[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill-huggingface-hf-mem":3,"mdc-onq5i5-key":38,"related-repo-huggingface-hf-mem":1105,"related-org-huggingface-hf-mem":1202},{"slug":4,"name":4,"fn":5,"description":6,"org":7,"tags":11,"stars":27,"repoUrl":28,"updatedAt":29,"license":30,"forks":31,"topics":32,"repo":33,"sourceUrl":36,"mdContent":37},"hf-mem","estimate memory for Hugging Face models","Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},"huggingface","Hugging Face","https:\u002F\u002Fpexgzepcugksgbtrxkhf.supabase.co\u002Fstorage\u002Fv1\u002Fobject\u002Fpublic\u002Forg-logos\u002Fhuggingface.png",[12,16,18,21,24],{"name":13,"slug":14,"type":15},"Performance","performance","tag",{"name":9,"slug":17,"type":15},"hugging-face",{"name":19,"slug":20,"type":15},"LLM","llm",{"name":22,"slug":23,"type":15},"CLI","cli",{"name":25,"slug":26,"type":15},"AI Infrastructure","ai-infrastructure",10861,"https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fskills","2026-06-13T07:23:57.101435",null,721,[],{"repoUrl":28,"stars":27,"forks":31,"topics":34,"description":35},[],"Give your agents the power of the Hugging Face ecosystem","https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fskills\u002Ftree\u002FHEAD\u002Fskills\u002Fhf-mem","---\nname: hf-mem\ndescription: Hugging Face CLI to estimate the required memory to load Safetensors or GGUF model weights for inference from the Hugging Face Hub\n---\n\n`hf_mem` estimates the required memory for inference, including model weights and an optional KV cache, for Safetensors and GGUF for models on the Hugging Face Hub using HTTP Range requests i.e., without downloading or loading any weights locally.\n\n## When to use?\n\n- User asks how much VRAM or memory a model needs to run\n- User wants to know if a model fits on their GPU or a given instance\n- User references a Hugging Face model ID or URL and asks about inference requirements\n\n## What are the requirements?\n\n- `uv` installed (for `uvx`)\n- `HF_TOKEN` env var or `--hf-token` flag (for gated or private models only)\n\n## How to run?\n\nRun with `--model-id` pointing to the Hugging Face Hub repository which will check that it either contains Safetensors (via `model.safetensors`, `model.safetensors.index.json` if sharded, or `model_index.json` for Diffusers) or GGUF model weights within.\n\n```bash\nuvx hf-mem --model-id \u003Cmodel-id> --json-output\n```\n\nIf the repository contains GGUF model weights in multiple precisions \u002F quantizations, the estimations will be on a per-file basis, whereas for inference you won't load all of those but rather only a single precision. This being said, for GGUF you might as well need to provide `--gguf-file` to target the specific file (or path if sharded) you want to run.\n\n```bash\nuvx hf-mem --model-id \u003Cmodel-id> --gguf-file \u003Cfile-or-path> --json-output\n```\n\nAdditionally, `hf-mem` comes with an `--experimental` flag that will also calculate the KV cache memory requirements too, useful for large-language models, meaning it applies to LLMs (`...ForCausalLM`), VLMs (`...ForConditionalGeneration`), and GGUF models.\n\nAs per the context window, it will be read from the default or overridden with `--max-model-len` a la vLLM. And, same goes for the KV cache precision, which will default to the model precision unless manually set via `--kv-cache-dtype` a la vLLM too.\n\nFor Safetensors use as:\n\n```bash\nuvx hf-mem --model-id \u003Cmodel-id> --experimental [--max-model-len N] [--batch-size N] [--kv-cache-dtype auto|bfloat16|fp8|fp8_ds_mla|fp8_e4m3|fp8_e5m2|fp8_inc] --json-output\n```\n\nAnd, for GGUF use as:\n\n```bash\nuvx hf-mem --model-id \u003Cmodel-id> --gguf-file \u003Cfile-or-path> --experimental [--max-model-len N] [--batch-size N] [--kv-cache-dtype auto|F32|F16|Q4_0|Q4_1|Q5_0|Q5_1|Q8_0|Q8_1|Q2_K|Q3_K|Q4_K|Q5_K|Q6_K|Q8_K|IQ2_XXS|IQ2_XS|IQ3_XXS|IQ1_S|IQ4_NL|IQ3_S|IQ2_S|IQ4_XS|I8|I16|I32|I64|F64|IQ1_M|BF16|TQ1_0|TQ2_0|MXFP4] --json-output\n```\n\n## Examples\n\nFor Transformers with Safetensors weights:\n\n```bash\nuvx hf-mem --model-id MiniMaxAI\u002FMiniMax-M2 --json-output\n```\n\nFor Diffusers with Safetensors weights:\n\n```bash\nuvx hf-mem --model-id Qwen\u002FQwen-Image --json-output\n```\n\nFor Sentence Transformers with Safetensors weights:\n\n```bash\nuvx hf-mem --model-id google\u002Fembeddinggemma-300m --json-output\n```\n\nWith `--experimental` to include the KV cache estimation for LLMs and VLMs:\n\n```bash\nuvx hf-mem --model-id mistralai\u002FMistral-7B-v0.1 --experimental --json-output\n```\n\nAnd, for LLMs or VLMs with GGUF weights:\n\n```bash\nuvx hf-mem --model-id unsloth\u002FQwen3.5-397B-A17B-GGUF --gguf-file Q4_K_M --experimental --json-output\n```\n",{"data":39,"body":40},{"name":4,"description":6},{"type":41,"children":42},"root",[43,58,65,85,91,132,138,175,235,248,313,349,370,375,506,511,889,895,900,931,936,967,972,1003,1015,1050,1055,1099],{"type":44,"tag":45,"props":46,"children":47},"element","p",{},[48,56],{"type":44,"tag":49,"props":50,"children":52},"code",{"className":51},[],[53],{"type":54,"value":55},"text","hf_mem",{"type":54,"value":57}," estimates the required memory for inference, including model weights and an optional KV cache, for Safetensors and GGUF for models on the Hugging Face Hub using HTTP Range requests i.e., without downloading or loading any weights locally.",{"type":44,"tag":59,"props":60,"children":62},"h2",{"id":61},"when-to-use",[63],{"type":54,"value":64},"When to use?",{"type":44,"tag":66,"props":67,"children":68},"ul",{},[69,75,80],{"type":44,"tag":70,"props":71,"children":72},"li",{},[73],{"type":54,"value":74},"User asks how much VRAM or memory a model needs to run",{"type":44,"tag":70,"props":76,"children":77},{},[78],{"type":54,"value":79},"User wants to know if a model fits on their GPU or a given instance",{"type":44,"tag":70,"props":81,"children":82},{},[83],{"type":54,"value":84},"User references a Hugging Face model ID or URL and asks about inference requirements",{"type":44,"tag":59,"props":86,"children":88},{"id":87},"what-are-the-requirements",[89],{"type":54,"value":90},"What are the requirements?",{"type":44,"tag":66,"props":92,"children":93},{},[94,113],{"type":44,"tag":70,"props":95,"children":96},{},[97,103,105,111],{"type":44,"tag":49,"props":98,"children":100},{"className":99},[],[101],{"type":54,"value":102},"uv",{"type":54,"value":104}," installed (for ",{"type":44,"tag":49,"props":106,"children":108},{"className":107},[],[109],{"type":54,"value":110},"uvx",{"type":54,"value":112},")",{"type":44,"tag":70,"props":114,"children":115},{},[116,122,124,130],{"type":44,"tag":49,"props":117,"children":119},{"className":118},[],[120],{"type":54,"value":121},"HF_TOKEN",{"type":54,"value":123}," env var or ",{"type":44,"tag":49,"props":125,"children":127},{"className":126},[],[128],{"type":54,"value":129},"--hf-token",{"type":54,"value":131}," flag (for gated or private models only)",{"type":44,"tag":59,"props":133,"children":135},{"id":134},"how-to-run",[136],{"type":54,"value":137},"How to run?",{"type":44,"tag":45,"props":139,"children":140},{},[141,143,149,151,157,159,165,167,173],{"type":54,"value":142},"Run with ",{"type":44,"tag":49,"props":144,"children":146},{"className":145},[],[147],{"type":54,"value":148},"--model-id",{"type":54,"value":150}," pointing to the Hugging Face Hub repository which will check that it either contains Safetensors (via ",{"type":44,"tag":49,"props":152,"children":154},{"className":153},[],[155],{"type":54,"value":156},"model.safetensors",{"type":54,"value":158},", ",{"type":44,"tag":49,"props":160,"children":162},{"className":161},[],[163],{"type":54,"value":164},"model.safetensors.index.json",{"type":54,"value":166}," if sharded, or ",{"type":44,"tag":49,"props":168,"children":170},{"className":169},[],[171],{"type":54,"value":172},"model_index.json",{"type":54,"value":174}," for Diffusers) or GGUF model weights within.",{"type":44,"tag":176,"props":177,"children":182},"pre",{"className":178,"code":179,"language":180,"meta":181,"style":181},"language-bash shiki shiki-themes material-theme-lighter material-theme material-theme-palenight","uvx hf-mem --model-id \u003Cmodel-id> --json-output\n","bash","",[183],{"type":44,"tag":49,"props":184,"children":185},{"__ignoreMap":181},[186],{"type":44,"tag":187,"props":188,"children":191},"span",{"class":189,"line":190},"line",1,[192,197,203,208,214,219,225,230],{"type":44,"tag":187,"props":193,"children":195},{"style":194},"--shiki-light:#E2931D;--shiki-default:#FFCB6B;--shiki-dark:#FFCB6B",[196],{"type":54,"value":110},{"type":44,"tag":187,"props":198,"children":200},{"style":199},"--shiki-light:#91B859;--shiki-default:#C3E88D;--shiki-dark:#C3E88D",[201],{"type":54,"value":202}," hf-mem",{"type":44,"tag":187,"props":204,"children":205},{"style":199},[206],{"type":54,"value":207}," --model-id",{"type":44,"tag":187,"props":209,"children":211},{"style":210},"--shiki-light:#39ADB5;--shiki-default:#89DDFF;--shiki-dark:#89DDFF",[212],{"type":54,"value":213}," \u003C",{"type":44,"tag":187,"props":215,"children":216},{"style":199},[217],{"type":54,"value":218},"model-i",{"type":44,"tag":187,"props":220,"children":222},{"style":221},"--shiki-light:#90A4AE;--shiki-default:#EEFFFF;--shiki-dark:#BABED8",[223],{"type":54,"value":224},"d",{"type":44,"tag":187,"props":226,"children":227},{"style":210},[228],{"type":54,"value":229},">",{"type":44,"tag":187,"props":231,"children":232},{"style":199},[233],{"type":54,"value":234}," --json-output\n",{"type":44,"tag":45,"props":236,"children":237},{},[238,240,246],{"type":54,"value":239},"If the repository contains GGUF model weights in multiple precisions \u002F quantizations, the estimations will be on a per-file basis, whereas for inference you won't load all of those but rather only a single precision. This being said, for GGUF you might as well need to provide ",{"type":44,"tag":49,"props":241,"children":243},{"className":242},[],[244],{"type":54,"value":245},"--gguf-file",{"type":54,"value":247}," to target the specific file (or path if sharded) you want to run.",{"type":44,"tag":176,"props":249,"children":251},{"className":178,"code":250,"language":180,"meta":181,"style":181},"uvx hf-mem --model-id \u003Cmodel-id> --gguf-file \u003Cfile-or-path> --json-output\n",[252],{"type":44,"tag":49,"props":253,"children":254},{"__ignoreMap":181},[255],{"type":44,"tag":187,"props":256,"children":257},{"class":189,"line":190},[258,262,266,270,274,278,282,286,291,295,300,305,309],{"type":44,"tag":187,"props":259,"children":260},{"style":194},[261],{"type":54,"value":110},{"type":44,"tag":187,"props":263,"children":264},{"style":199},[265],{"type":54,"value":202},{"type":44,"tag":187,"props":267,"children":268},{"style":199},[269],{"type":54,"value":207},{"type":44,"tag":187,"props":271,"children":272},{"style":210},[273],{"type":54,"value":213},{"type":44,"tag":187,"props":275,"children":276},{"style":199},[277],{"type":54,"value":218},{"type":44,"tag":187,"props":279,"children":280},{"style":221},[281],{"type":54,"value":224},{"type":44,"tag":187,"props":283,"children":284},{"style":210},[285],{"type":54,"value":229},{"type":44,"tag":187,"props":287,"children":288},{"style":199},[289],{"type":54,"value":290}," --gguf-file",{"type":44,"tag":187,"props":292,"children":293},{"style":210},[294],{"type":54,"value":213},{"type":44,"tag":187,"props":296,"children":297},{"style":199},[298],{"type":54,"value":299},"file-or-pat",{"type":44,"tag":187,"props":301,"children":302},{"style":221},[303],{"type":54,"value":304},"h",{"type":44,"tag":187,"props":306,"children":307},{"style":210},[308],{"type":54,"value":229},{"type":44,"tag":187,"props":310,"children":311},{"style":199},[312],{"type":54,"value":234},{"type":44,"tag":45,"props":314,"children":315},{},[316,318,323,325,331,333,339,341,347],{"type":54,"value":317},"Additionally, ",{"type":44,"tag":49,"props":319,"children":321},{"className":320},[],[322],{"type":54,"value":4},{"type":54,"value":324}," comes with an ",{"type":44,"tag":49,"props":326,"children":328},{"className":327},[],[329],{"type":54,"value":330},"--experimental",{"type":54,"value":332}," flag that will also calculate the KV cache memory requirements too, useful for large-language models, meaning it applies to LLMs (",{"type":44,"tag":49,"props":334,"children":336},{"className":335},[],[337],{"type":54,"value":338},"...ForCausalLM",{"type":54,"value":340},"), VLMs (",{"type":44,"tag":49,"props":342,"children":344},{"className":343},[],[345],{"type":54,"value":346},"...ForConditionalGeneration",{"type":54,"value":348},"), and GGUF models.",{"type":44,"tag":45,"props":350,"children":351},{},[352,354,360,362,368],{"type":54,"value":353},"As per the context window, it will be read from the default or overridden with ",{"type":44,"tag":49,"props":355,"children":357},{"className":356},[],[358],{"type":54,"value":359},"--max-model-len",{"type":54,"value":361}," a la vLLM. And, same goes for the KV cache precision, which will default to the model precision unless manually set via ",{"type":44,"tag":49,"props":363,"children":365},{"className":364},[],[366],{"type":54,"value":367},"--kv-cache-dtype",{"type":54,"value":369}," a la vLLM too.",{"type":44,"tag":45,"props":371,"children":372},{},[373],{"type":54,"value":374},"For Safetensors use as:",{"type":44,"tag":176,"props":376,"children":378},{"className":178,"code":377,"language":180,"meta":181,"style":181},"uvx hf-mem --model-id \u003Cmodel-id> --experimental [--max-model-len N] [--batch-size N] [--kv-cache-dtype auto|bfloat16|fp8|fp8_ds_mla|fp8_e4m3|fp8_e5m2|fp8_inc] --json-output\n",[379],{"type":44,"tag":49,"props":380,"children":381},{"__ignoreMap":181},[382],{"type":44,"tag":187,"props":383,"children":384},{"class":189,"line":190},[385,389,393,397,401,405,409,413,418,423,428,433,437,442,447,452,457,461,466,470,475,479,484,488,493,497,502],{"type":44,"tag":187,"props":386,"children":387},{"style":194},[388],{"type":54,"value":110},{"type":44,"tag":187,"props":390,"children":391},{"style":199},[392],{"type":54,"value":202},{"type":44,"tag":187,"props":394,"children":395},{"style":199},[396],{"type":54,"value":207},{"type":44,"tag":187,"props":398,"children":399},{"style":210},[400],{"type":54,"value":213},{"type":44,"tag":187,"props":402,"children":403},{"style":199},[404],{"type":54,"value":218},{"type":44,"tag":187,"props":406,"children":407},{"style":221},[408],{"type":54,"value":224},{"type":44,"tag":187,"props":410,"children":411},{"style":210},[412],{"type":54,"value":229},{"type":44,"tag":187,"props":414,"children":415},{"style":199},[416],{"type":54,"value":417}," --experimental",{"type":44,"tag":187,"props":419,"children":420},{"style":221},[421],{"type":54,"value":422}," [--max-model-len ",{"type":44,"tag":187,"props":424,"children":425},{"style":199},[426],{"type":54,"value":427},"N]",{"type":44,"tag":187,"props":429,"children":430},{"style":221},[431],{"type":54,"value":432}," [--batch-size ",{"type":44,"tag":187,"props":434,"children":435},{"style":199},[436],{"type":54,"value":427},{"type":44,"tag":187,"props":438,"children":439},{"style":221},[440],{"type":54,"value":441}," [--kv-cache-dtype ",{"type":44,"tag":187,"props":443,"children":444},{"style":199},[445],{"type":54,"value":446},"auto",{"type":44,"tag":187,"props":448,"children":449},{"style":210},[450],{"type":54,"value":451},"|",{"type":44,"tag":187,"props":453,"children":454},{"style":194},[455],{"type":54,"value":456},"bfloat16",{"type":44,"tag":187,"props":458,"children":459},{"style":210},[460],{"type":54,"value":451},{"type":44,"tag":187,"props":462,"children":463},{"style":194},[464],{"type":54,"value":465},"fp8",{"type":44,"tag":187,"props":467,"children":468},{"style":210},[469],{"type":54,"value":451},{"type":44,"tag":187,"props":471,"children":472},{"style":194},[473],{"type":54,"value":474},"fp8_ds_mla",{"type":44,"tag":187,"props":476,"children":477},{"style":210},[478],{"type":54,"value":451},{"type":44,"tag":187,"props":480,"children":481},{"style":194},[482],{"type":54,"value":483},"fp8_e4m3",{"type":44,"tag":187,"props":485,"children":486},{"style":210},[487],{"type":54,"value":451},{"type":44,"tag":187,"props":489,"children":490},{"style":194},[491],{"type":54,"value":492},"fp8_e5m2",{"type":44,"tag":187,"props":494,"children":495},{"style":210},[496],{"type":54,"value":451},{"type":44,"tag":187,"props":498,"children":499},{"style":194},[500],{"type":54,"value":501},"fp8_inc]",{"type":44,"tag":187,"props":503,"children":504},{"style":199},[505],{"type":54,"value":234},{"type":44,"tag":45,"props":507,"children":508},{},[509],{"type":54,"value":510},"And, for GGUF use as:",{"type":44,"tag":176,"props":512,"children":514},{"className":178,"code":513,"language":180,"meta":181,"style":181},"uvx hf-mem --model-id \u003Cmodel-id> --gguf-file \u003Cfile-or-path> --experimental [--max-model-len N] [--batch-size N] [--kv-cache-dtype auto|F32|F16|Q4_0|Q4_1|Q5_0|Q5_1|Q8_0|Q8_1|Q2_K|Q3_K|Q4_K|Q5_K|Q6_K|Q8_K|IQ2_XXS|IQ2_XS|IQ3_XXS|IQ1_S|IQ4_NL|IQ3_S|IQ2_S|IQ4_XS|I8|I16|I32|I64|F64|IQ1_M|BF16|TQ1_0|TQ2_0|MXFP4] --json-output\n",[515],{"type":44,"tag":49,"props":516,"children":517},{"__ignoreMap":181},[518],{"type":44,"tag":187,"props":519,"children":520},{"class":189,"line":190},[521,525,529,533,537,541,545,549,553,557,561,565,569,573,577,581,585,589,593,597,601,606,610,615,619,624,628,633,637,642,646,651,655,660,664,669,673,678,682,687,691,696,700,705,709,714,718,723,727,732,736,741,745,750,754,759,763,768,772,777,781,786,790,795,799,804,808,813,817,822,826,831,835,840,844,849,853,858,862,867,871,876,880,885],{"type":44,"tag":187,"props":522,"children":523},{"style":194},[524],{"type":54,"value":110},{"type":44,"tag":187,"props":526,"children":527},{"style":199},[528],{"type":54,"value":202},{"type":44,"tag":187,"props":530,"children":531},{"style":199},[532],{"type":54,"value":207},{"type":44,"tag":187,"props":534,"children":535},{"style":210},[536],{"type":54,"value":213},{"type":44,"tag":187,"props":538,"children":539},{"style":199},[540],{"type":54,"value":218},{"type":44,"tag":187,"props":542,"children":543},{"style":221},[544],{"type":54,"value":224},{"type":44,"tag":187,"props":546,"children":547},{"style":210},[548],{"type":54,"value":229},{"type":44,"tag":187,"props":550,"children":551},{"style":199},[552],{"type":54,"value":290},{"type":44,"tag":187,"props":554,"children":555},{"style":210},[556],{"type":54,"value":213},{"type":44,"tag":187,"props":558,"children":559},{"style":199},[560],{"type":54,"value":299},{"type":44,"tag":187,"props":562,"children":563},{"style":221},[564],{"type":54,"value":304},{"type":44,"tag":187,"props":566,"children":567},{"style":210},[568],{"type":54,"value":229},{"type":44,"tag":187,"props":570,"children":571},{"style":199},[572],{"type":54,"value":417},{"type":44,"tag":187,"props":574,"children":575},{"style":221},[576],{"type":54,"value":422},{"type":44,"tag":187,"props":578,"children":579},{"style":199},[580],{"type":54,"value":427},{"type":44,"tag":187,"props":582,"children":583},{"style":221},[584],{"type":54,"value":432},{"type":44,"tag":187,"props":586,"children":587},{"style":199},[588],{"type":54,"value":427},{"type":44,"tag":187,"props":590,"children":591},{"style":221},[592],{"type":54,"value":441},{"type":44,"tag":187,"props":594,"children":595},{"style":199},[596],{"type":54,"value":446},{"type":44,"tag":187,"props":598,"children":599},{"style":210},[600],{"type":54,"value":451},{"type":44,"tag":187,"props":602,"children":603},{"style":194},[604],{"type":54,"value":605},"F32",{"type":44,"tag":187,"props":607,"children":608},{"style":210},[609],{"type":54,"value":451},{"type":44,"tag":187,"props":611,"children":612},{"style":194},[613],{"type":54,"value":614},"F16",{"type":44,"tag":187,"props":616,"children":617},{"style":210},[618],{"type":54,"value":451},{"type":44,"tag":187,"props":620,"children":621},{"style":194},[622],{"type":54,"value":623},"Q4_0",{"type":44,"tag":187,"props":625,"children":626},{"style":210},[627],{"type":54,"value":451},{"type":44,"tag":187,"props":629,"children":630},{"style":194},[631],{"type":54,"value":632},"Q4_1",{"type":44,"tag":187,"props":634,"children":635},{"style":210},[636],{"type":54,"value":451},{"type":44,"tag":187,"props":638,"children":639},{"style":194},[640],{"type":54,"value":641},"Q5_0",{"type":44,"tag":187,"props":643,"children":644},{"style":210},[645],{"type":54,"value":451},{"type":44,"tag":187,"props":647,"children":648},{"style":194},[649],{"type":54,"value":650},"Q5_1",{"type":44,"tag":187,"props":652,"children":653},{"style":210},[654],{"type":54,"value":451},{"type":44,"tag":187,"props":656,"children":657},{"style":194},[658],{"type":54,"value":659},"Q8_0",{"type":44,"tag":187,"props":661,"children":662},{"style":210},[663],{"type":54,"value":451},{"type":44,"tag":187,"props":665,"children":666},{"style":194},[667],{"type":54,"value":668},"Q8_1",{"type":44,"tag":187,"props":670,"children":671},{"style":210},[672],{"type":54,"value":451},{"type":44,"tag":187,"props":674,"children":675},{"style":194},[676],{"type":54,"value":677},"Q2_K",{"type":44,"tag":187,"props":679,"children":680},{"style":210},[681],{"type":54,"value":451},{"type":44,"tag":187,"props":683,"children":684},{"style":194},[685],{"type":54,"value":686},"Q3_K",{"type":44,"tag":187,"props":688,"children":689},{"style":210},[690],{"type":54,"value":451},{"type":44,"tag":187,"props":692,"children":693},{"style":194},[694],{"type":54,"value":695},"Q4_K",{"type":44,"tag":187,"props":697,"children":698},{"style":210},[699],{"type":54,"value":451},{"type":44,"tag":187,"props":701,"children":702},{"style":194},[703],{"type":54,"value":704},"Q5_K",{"type":44,"tag":187,"props":706,"children":707},{"style":210},[708],{"type":54,"value":451},{"type":44,"tag":187,"props":710,"children":711},{"style":194},[712],{"type":54,"value":713},"Q6_K",{"type":44,"tag":187,"props":715,"children":716},{"style":210},[717],{"type":54,"value":451},{"type":44,"tag":187,"props":719,"children":720},{"style":194},[721],{"type":54,"value":722},"Q8_K",{"type":44,"tag":187,"props":724,"children":725},{"style":210},[726],{"type":54,"value":451},{"type":44,"tag":187,"props":728,"children":729},{"style":194},[730],{"type":54,"value":731},"IQ2_XXS",{"type":44,"tag":187,"props":733,"children":734},{"style":210},[735],{"type":54,"value":451},{"type":44,"tag":187,"props":737,"children":738},{"style":194},[739],{"type":54,"value":740},"IQ2_XS",{"type":44,"tag":187,"props":742,"children":743},{"style":210},[744],{"type":54,"value":451},{"type":44,"tag":187,"props":746,"children":747},{"style":194},[748],{"type":54,"value":749},"IQ3_XXS",{"type":44,"tag":187,"props":751,"children":752},{"style":210},[753],{"type":54,"value":451},{"type":44,"tag":187,"props":755,"children":756},{"style":194},[757],{"type":54,"value":758},"IQ1_S",{"type":44,"tag":187,"props":760,"children":761},{"style":210},[762],{"type":54,"value":451},{"type":44,"tag":187,"props":764,"children":765},{"style":194},[766],{"type":54,"value":767},"IQ4_NL",{"type":44,"tag":187,"props":769,"children":770},{"style":210},[771],{"type":54,"value":451},{"type":44,"tag":187,"props":773,"children":774},{"style":194},[775],{"type":54,"value":776},"IQ3_S",{"type":44,"tag":187,"props":778,"children":779},{"style":210},[780],{"type":54,"value":451},{"type":44,"tag":187,"props":782,"children":783},{"style":194},[784],{"type":54,"value":785},"IQ2_S",{"type":44,"tag":187,"props":787,"children":788},{"style":210},[789],{"type":54,"value":451},{"type":44,"tag":187,"props":791,"children":792},{"style":194},[793],{"type":54,"value":794},"IQ4_XS",{"type":44,"tag":187,"props":796,"children":797},{"style":210},[798],{"type":54,"value":451},{"type":44,"tag":187,"props":800,"children":801},{"style":194},[802],{"type":54,"value":803},"I8",{"type":44,"tag":187,"props":805,"children":806},{"style":210},[807],{"type":54,"value":451},{"type":44,"tag":187,"props":809,"children":810},{"style":194},[811],{"type":54,"value":812},"I16",{"type":44,"tag":187,"props":814,"children":815},{"style":210},[816],{"type":54,"value":451},{"type":44,"tag":187,"props":818,"children":819},{"style":194},[820],{"type":54,"value":821},"I32",{"type":44,"tag":187,"props":823,"children":824},{"style":210},[825],{"type":54,"value":451},{"type":44,"tag":187,"props":827,"children":828},{"style":194},[829],{"type":54,"value":830},"I64",{"type":44,"tag":187,"props":832,"children":833},{"style":210},[834],{"type":54,"value":451},{"type":44,"tag":187,"props":836,"children":837},{"style":194},[838],{"type":54,"value":839},"F64",{"type":44,"tag":187,"props":841,"children":842},{"style":210},[843],{"type":54,"value":451},{"type":44,"tag":187,"props":845,"children":846},{"style":194},[847],{"type":54,"value":848},"IQ1_M",{"type":44,"tag":187,"props":850,"children":851},{"style":210},[852],{"type":54,"value":451},{"type":44,"tag":187,"props":854,"children":855},{"style":194},[856],{"type":54,"value":857},"BF16",{"type":44,"tag":187,"props":859,"children":860},{"style":210},[861],{"type":54,"value":451},{"type":44,"tag":187,"props":863,"children":864},{"style":194},[865],{"type":54,"value":866},"TQ1_0",{"type":44,"tag":187,"props":868,"children":869},{"style":210},[870],{"type":54,"value":451},{"type":44,"tag":187,"props":872,"children":873},{"style":194},[874],{"type":54,"value":875},"TQ2_0",{"type":44,"tag":187,"props":877,"children":878},{"style":210},[879],{"type":54,"value":451},{"type":44,"tag":187,"props":881,"children":882},{"style":194},[883],{"type":54,"value":884},"MXFP4]",{"type":44,"tag":187,"props":886,"children":887},{"style":199},[888],{"type":54,"value":234},{"type":44,"tag":59,"props":890,"children":892},{"id":891},"examples",[893],{"type":54,"value":894},"Examples",{"type":44,"tag":45,"props":896,"children":897},{},[898],{"type":54,"value":899},"For Transformers with Safetensors weights:",{"type":44,"tag":176,"props":901,"children":903},{"className":178,"code":902,"language":180,"meta":181,"style":181},"uvx hf-mem --model-id MiniMaxAI\u002FMiniMax-M2 --json-output\n",[904],{"type":44,"tag":49,"props":905,"children":906},{"__ignoreMap":181},[907],{"type":44,"tag":187,"props":908,"children":909},{"class":189,"line":190},[910,914,918,922,927],{"type":44,"tag":187,"props":911,"children":912},{"style":194},[913],{"type":54,"value":110},{"type":44,"tag":187,"props":915,"children":916},{"style":199},[917],{"type":54,"value":202},{"type":44,"tag":187,"props":919,"children":920},{"style":199},[921],{"type":54,"value":207},{"type":44,"tag":187,"props":923,"children":924},{"style":199},[925],{"type":54,"value":926}," MiniMaxAI\u002FMiniMax-M2",{"type":44,"tag":187,"props":928,"children":929},{"style":199},[930],{"type":54,"value":234},{"type":44,"tag":45,"props":932,"children":933},{},[934],{"type":54,"value":935},"For Diffusers with Safetensors weights:",{"type":44,"tag":176,"props":937,"children":939},{"className":178,"code":938,"language":180,"meta":181,"style":181},"uvx hf-mem --model-id Qwen\u002FQwen-Image --json-output\n",[940],{"type":44,"tag":49,"props":941,"children":942},{"__ignoreMap":181},[943],{"type":44,"tag":187,"props":944,"children":945},{"class":189,"line":190},[946,950,954,958,963],{"type":44,"tag":187,"props":947,"children":948},{"style":194},[949],{"type":54,"value":110},{"type":44,"tag":187,"props":951,"children":952},{"style":199},[953],{"type":54,"value":202},{"type":44,"tag":187,"props":955,"children":956},{"style":199},[957],{"type":54,"value":207},{"type":44,"tag":187,"props":959,"children":960},{"style":199},[961],{"type":54,"value":962}," Qwen\u002FQwen-Image",{"type":44,"tag":187,"props":964,"children":965},{"style":199},[966],{"type":54,"value":234},{"type":44,"tag":45,"props":968,"children":969},{},[970],{"type":54,"value":971},"For Sentence Transformers with Safetensors weights:",{"type":44,"tag":176,"props":973,"children":975},{"className":178,"code":974,"language":180,"meta":181,"style":181},"uvx hf-mem --model-id google\u002Fembeddinggemma-300m --json-output\n",[976],{"type":44,"tag":49,"props":977,"children":978},{"__ignoreMap":181},[979],{"type":44,"tag":187,"props":980,"children":981},{"class":189,"line":190},[982,986,990,994,999],{"type":44,"tag":187,"props":983,"children":984},{"style":194},[985],{"type":54,"value":110},{"type":44,"tag":187,"props":987,"children":988},{"style":199},[989],{"type":54,"value":202},{"type":44,"tag":187,"props":991,"children":992},{"style":199},[993],{"type":54,"value":207},{"type":44,"tag":187,"props":995,"children":996},{"style":199},[997],{"type":54,"value":998}," google\u002Fembeddinggemma-300m",{"type":44,"tag":187,"props":1000,"children":1001},{"style":199},[1002],{"type":54,"value":234},{"type":44,"tag":45,"props":1004,"children":1005},{},[1006,1008,1013],{"type":54,"value":1007},"With ",{"type":44,"tag":49,"props":1009,"children":1011},{"className":1010},[],[1012],{"type":54,"value":330},{"type":54,"value":1014}," to include the KV cache estimation for LLMs and VLMs:",{"type":44,"tag":176,"props":1016,"children":1018},{"className":178,"code":1017,"language":180,"meta":181,"style":181},"uvx hf-mem --model-id mistralai\u002FMistral-7B-v0.1 --experimental --json-output\n",[1019],{"type":44,"tag":49,"props":1020,"children":1021},{"__ignoreMap":181},[1022],{"type":44,"tag":187,"props":1023,"children":1024},{"class":189,"line":190},[1025,1029,1033,1037,1042,1046],{"type":44,"tag":187,"props":1026,"children":1027},{"style":194},[1028],{"type":54,"value":110},{"type":44,"tag":187,"props":1030,"children":1031},{"style":199},[1032],{"type":54,"value":202},{"type":44,"tag":187,"props":1034,"children":1035},{"style":199},[1036],{"type":54,"value":207},{"type":44,"tag":187,"props":1038,"children":1039},{"style":199},[1040],{"type":54,"value":1041}," mistralai\u002FMistral-7B-v0.1",{"type":44,"tag":187,"props":1043,"children":1044},{"style":199},[1045],{"type":54,"value":417},{"type":44,"tag":187,"props":1047,"children":1048},{"style":199},[1049],{"type":54,"value":234},{"type":44,"tag":45,"props":1051,"children":1052},{},[1053],{"type":54,"value":1054},"And, for LLMs or VLMs with GGUF weights:",{"type":44,"tag":176,"props":1056,"children":1058},{"className":178,"code":1057,"language":180,"meta":181,"style":181},"uvx hf-mem --model-id unsloth\u002FQwen3.5-397B-A17B-GGUF --gguf-file Q4_K_M --experimental --json-output\n",[1059],{"type":44,"tag":49,"props":1060,"children":1061},{"__ignoreMap":181},[1062],{"type":44,"tag":187,"props":1063,"children":1064},{"class":189,"line":190},[1065,1069,1073,1077,1082,1086,1091,1095],{"type":44,"tag":187,"props":1066,"children":1067},{"style":194},[1068],{"type":54,"value":110},{"type":44,"tag":187,"props":1070,"children":1071},{"style":199},[1072],{"type":54,"value":202},{"type":44,"tag":187,"props":1074,"children":1075},{"style":199},[1076],{"type":54,"value":207},{"type":44,"tag":187,"props":1078,"children":1079},{"style":199},[1080],{"type":54,"value":1081}," unsloth\u002FQwen3.5-397B-A17B-GGUF",{"type":44,"tag":187,"props":1083,"children":1084},{"style":199},[1085],{"type":54,"value":290},{"type":44,"tag":187,"props":1087,"children":1088},{"style":199},[1089],{"type":54,"value":1090}," Q4_K_M",{"type":44,"tag":187,"props":1092,"children":1093},{"style":199},[1094],{"type":54,"value":417},{"type":44,"tag":187,"props":1096,"children":1097},{"style":199},[1098],{"type":54,"value":234},{"type":44,"tag":1100,"props":1101,"children":1102},"style",{},[1103],{"type":54,"value":1104},"html .light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html.light .shiki span {color: var(--shiki-light);background: var(--shiki-light-bg);font-style: var(--shiki-light-font-style);font-weight: var(--shiki-light-font-weight);text-decoration: var(--shiki-light-text-decoration);}html .default .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .shiki span {color: var(--shiki-default);background: var(--shiki-default-bg);font-style: var(--shiki-default-font-style);font-weight: var(--shiki-default-font-weight);text-decoration: var(--shiki-default-text-decoration);}html .dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}html.dark .shiki span {color: var(--shiki-dark);background: var(--shiki-dark-bg);font-style: var(--shiki-dark-font-style);font-weight: var(--shiki-dark-font-weight);text-decoration: var(--shiki-dark-text-decoration);}",{"items":1106,"total":1201},[1107,1120,1134,1149,1162,1177,1191],{"slug":1108,"name":1108,"fn":1109,"description":1110,"org":1111,"tags":1112,"stars":27,"repoUrl":28,"updatedAt":1119},"hf-cli","manage Hugging Face Hub resources via CLI","Hugging Face Hub CLI (`hf`) for downloading, uploading, and managing models, datasets, spaces, buckets, repos, papers, jobs, and more on the Hugging Face Hub. Use when: handling authentication; managing local cache; managing Hugging Face Buckets; running or scheduling jobs on Hugging Face infrastructure; managing Hugging Face repos; discussions and pull requests; browsing models, datasets and spaces; reading, searching, or browsing academic papers; managing collections; querying datasets; configuring spaces; setting up webhooks; or deploying and managing HF Inference Endpoints. Make sure to use this skill whenever the user mentions 'hf', 'huggingface', 'Hugging Face', 'huggingface-cli', or 'hugging face cli', or wants to do anything related to the Hugging Face ecosystem and to AI and ML in general. Also use for cloud storage needs like training checkpoints, data pipelines, or agent traces. Use even if the user doesn't explicitly ask for a CLI command. Replaces the deprecated `huggingface-cli`.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1113,1114,1117,1118],{"name":22,"slug":23,"type":15},{"name":1115,"slug":1116,"type":15},"Datasets","datasets",{"name":9,"slug":17,"type":15},{"name":19,"slug":20,"type":15},"2026-04-06T18:25:34.020855",{"slug":1121,"name":1121,"fn":1122,"description":1123,"org":1124,"tags":1125,"stars":27,"repoUrl":28,"updatedAt":1133},"hf-cloud-aws-context-discovery","discover local AWS environment context","Discover the user's local AWS context (active profile, region, account ID, caller identity) at the start of any AWS task. Use this skill before any other AWS work — deploying to SageMaker, creating resources, calling AWS APIs, or anything that touches an AWS account. Use it especially when the user has not specified a region or profile explicitly, when they say things like \"use my AWS account\", \"deploy to AWS\", \"use my profile\", or when about to make any AWS CLI or SDK call. Never guess the region or account ID — always use this skill to read it from the local configuration first.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1126,1129,1130],{"name":1127,"slug":1128,"type":15},"AWS","aws",{"name":22,"slug":23,"type":15},{"name":1131,"slug":1132,"type":15},"Configuration","configuration","2026-07-08T05:55:33.716099",{"slug":1135,"name":1135,"fn":1136,"description":1137,"org":1138,"tags":1139,"stars":27,"repoUrl":28,"updatedAt":1148},"hf-cloud-python-env-setup","set up Python environments for AWS","Set up an isolated Python environment for SageMaker \u002F AWS work, with the right Python version and current boto3. Use this skill whenever Python code will be executed for a SageMaker deployment, training job, or any AWS automation — including when about to run `pip install`, when about to invoke `boto3`, when creating or activating a virtualenv, or when the user asks to \"set up the environment\". Never use system Python and never `pip install` into it. Always isolate. This skill prevents the most common failure modes: wrong Python version, dependency conflicts, and stale SDKs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1140,1141,1142,1145],{"name":25,"slug":26,"type":15},{"name":1127,"slug":1128,"type":15},{"name":1143,"slug":1144,"type":15},"Engineering","engineering",{"name":1146,"slug":1147,"type":15},"Python","python","2026-07-08T05:55:32.505017",{"slug":1150,"name":1150,"fn":1151,"description":1152,"org":1153,"tags":1154,"stars":27,"repoUrl":28,"updatedAt":1161},"hf-cloud-sagemaker-deployment-planner","plan model deployments to Amazon SageMaker","Plan and coordinate the deployment of a model to Amazon SageMaker AI. Use this skill whenever the user wants to deploy, host, serve, or expose a model on SageMaker or AWS — including phrases like \"deploy a model\", \"host this LLM on AWS\", \"serve this embedding model\", \"deploy a reranker\", \"deploy a text-to-image \u002F diffusion model\", \"host this for async inference\", \"create an endpoint\", \"serve my fine-tuned model\", or any request that involves making a model available for inference on AWS. Use this even when the user is vague (e.g. \"I just want to get this running on AWS, you figure it out\"). Works for text-generation LLMs, embedding models, rerankers, classifiers, text-to-image \u002F diffusion models — picks the right serving stack and chooses between real-time and async inference. This is the entry-point skill for SageMaker deployment work — it asks clarifying questions, picks a deployment pathway, and coordinates the other deployment skills.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1155,1156,1157,1160],{"name":25,"slug":26,"type":15},{"name":1127,"slug":1128,"type":15},{"name":1158,"slug":1159,"type":15},"Deployment","deployment",{"name":9,"slug":17,"type":15},"2026-07-08T05:55:37.387689",{"slug":1163,"name":1163,"fn":1164,"description":1165,"org":1166,"tags":1167,"stars":27,"repoUrl":28,"updatedAt":1176},"hf-cloud-sagemaker-iam-preflight","configure SageMaker IAM roles","Ensure a usable SageMaker execution role exists before deploying or training. Use this skill whenever about to create a SageMaker endpoint, model, training job, or any resource that requires an execution role. Use it especially when the user has not provided a role ARN explicitly, when scripts are about to call `iam:CreateRole`, or when an AccessDenied error mentions an IAM action. Never blindly call `iam:CreateRole` — always check for existing roles first. This skill prevents the most common SageMaker deployment failure: trying to create IAM resources from an SSO principal that has no IAM write permissions.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1168,1169,1170,1173],{"name":25,"slug":26,"type":15},{"name":1127,"slug":1128,"type":15},{"name":1171,"slug":1172,"type":15},"Permissions","permissions",{"name":1174,"slug":1175,"type":15},"Security","security","2026-07-08T05:55:34.948771",{"slug":1178,"name":1178,"fn":1179,"description":1180,"org":1181,"tags":1182,"stars":27,"repoUrl":28,"updatedAt":1190},"hf-cloud-sagemaker-production-defaults","create production-ready SageMaker endpoints","Create a SageMaker endpoint (real-time or async) with autoscaling, CloudWatch alarms, and tagging enabled by default. Use this skill whenever about to create a SageMaker endpoint, write deployment code that calls `create_endpoint`, or finalize a deployment after the image URI and IAM role are known. Provides deploy.py for real-time endpoints and deploy_async.py for async endpoints (with genuine scale-to-zero support). This is the last step in the SageMaker deployment workflow. Never generate a bare `create_endpoint` call without these defaults — endpoints without autoscaling or alarms are demos, not deployments.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1183,1184,1185,1186,1187],{"name":25,"slug":26,"type":15},{"name":1127,"slug":1128,"type":15},{"name":1158,"slug":1159,"type":15},{"name":9,"slug":17,"type":15},{"name":1188,"slug":1189,"type":15},"Monitoring","monitoring","2026-07-08T05:55:38.664702",{"slug":1192,"name":1192,"fn":1193,"description":1194,"org":1195,"tags":1196,"stars":27,"repoUrl":28,"updatedAt":1200},"hf-cloud-serving-image-selection","select SageMaker serving containers","Pick the right serving container for a SageMaker model deployment and find its current image URI. Use this skill whenever about to deploy a model to a SageMaker endpoint and an image URI needs to be chosen — including when the user says \"deploy this LLM\", \"host this HuggingFace model\", \"serve this fine-tuned model\", \"deploy this embedding model\", \"host a reranker\", \"serve a sentence-transformers model\", or when about to hardcode any container URI in deployment code. HuggingFace-curated Deep Learning Containers are ALWAYS preferred: HuggingFace vLLM (LLMs and generative rerankers), HuggingFace vLLM-Omni (multimodal), TEI (embeddings\u002Fcross-encoder rerankers), HF Inference Toolkit (other transformers). Generic images (AWS vLLM, DJL-LMI, SGLang) are used only when no HuggingFace image is compatible — never merely because they carry a newer version. Never hardcode a container URI from memory and never default to TGI. Prevents stale-image failures and wrong-region URIs.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1197,1198,1199],{"name":25,"slug":26,"type":15},{"name":1127,"slug":1128,"type":15},{"name":1158,"slug":1159,"type":15},"2026-07-08T05:55:36.173465",24,{"items":1203,"total":1320},[1204,1222,1236,1243,1249,1256,1263,1270,1278,1284,1297,1305],{"slug":1205,"name":1205,"fn":1206,"description":1207,"org":1208,"tags":1209,"stars":1219,"repoUrl":1220,"updatedAt":1221},"train-sentence-transformers","train sentence-transformers models","Train or fine-tune sentence-transformers models across `SentenceTransformer` (bi-encoder; dense or static embedding model; for retrieval, similarity, clustering, classification, paraphrase mining, dedup, multimodal), `CrossEncoder` (reranker; pair scoring for two-stage retrieval \u002F pair classification), and `SparseEncoder` (SPLADE, sparse embedding model; for learned-sparse retrieval). Covers loss selection, hard-negative mining, evaluators, distillation, LoRA, Matryoshka, and Hugging Face Hub publishing. Use for any sentence-transformers training task.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1210,1213,1214,1215,1216],{"name":1211,"slug":1212,"type":15},"Deep Learning","deep-learning",{"name":9,"slug":17,"type":15},{"name":19,"slug":20,"type":15},{"name":1146,"slug":1147,"type":15},{"name":1217,"slug":1218,"type":15},"Search","search",18914,"https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Fsentence-transformers","2026-05-08T05:09:16.820066",{"slug":1223,"name":1223,"fn":1224,"description":1225,"org":1226,"tags":1227,"stars":1233,"repoUrl":1234,"updatedAt":1235},"trl-training","train and fine-tune LLMs with TRL","Train and fine-tune transformer language models using TRL (Transformers Reinforcement Learning). Supports SFT, DPO, GRPO, KTO, RLOO and Reward Model training via CLI commands.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1228,1229,1230,1231,1232],{"name":25,"slug":26,"type":15},{"name":1211,"slug":1212,"type":15},{"name":9,"slug":17,"type":15},{"name":19,"slug":20,"type":15},{"name":1146,"slug":1147,"type":15},18850,"https:\u002F\u002Fgithub.com\u002Fhuggingface\u002Ftrl","2026-04-06T18:25:32.746828",{"slug":1108,"name":1108,"fn":1109,"description":1110,"org":1237,"tags":1238,"stars":27,"repoUrl":28,"updatedAt":1119},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1239,1240,1241,1242],{"name":22,"slug":23,"type":15},{"name":1115,"slug":1116,"type":15},{"name":9,"slug":17,"type":15},{"name":19,"slug":20,"type":15},{"slug":1121,"name":1121,"fn":1122,"description":1123,"org":1244,"tags":1245,"stars":27,"repoUrl":28,"updatedAt":1133},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1246,1247,1248],{"name":1127,"slug":1128,"type":15},{"name":22,"slug":23,"type":15},{"name":1131,"slug":1132,"type":15},{"slug":1135,"name":1135,"fn":1136,"description":1137,"org":1250,"tags":1251,"stars":27,"repoUrl":28,"updatedAt":1148},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1252,1253,1254,1255],{"name":25,"slug":26,"type":15},{"name":1127,"slug":1128,"type":15},{"name":1143,"slug":1144,"type":15},{"name":1146,"slug":1147,"type":15},{"slug":1150,"name":1150,"fn":1151,"description":1152,"org":1257,"tags":1258,"stars":27,"repoUrl":28,"updatedAt":1161},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1259,1260,1261,1262],{"name":25,"slug":26,"type":15},{"name":1127,"slug":1128,"type":15},{"name":1158,"slug":1159,"type":15},{"name":9,"slug":17,"type":15},{"slug":1163,"name":1163,"fn":1164,"description":1165,"org":1264,"tags":1265,"stars":27,"repoUrl":28,"updatedAt":1176},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1266,1267,1268,1269],{"name":25,"slug":26,"type":15},{"name":1127,"slug":1128,"type":15},{"name":1171,"slug":1172,"type":15},{"name":1174,"slug":1175,"type":15},{"slug":1178,"name":1178,"fn":1179,"description":1180,"org":1271,"tags":1272,"stars":27,"repoUrl":28,"updatedAt":1190},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1273,1274,1275,1276,1277],{"name":25,"slug":26,"type":15},{"name":1127,"slug":1128,"type":15},{"name":1158,"slug":1159,"type":15},{"name":9,"slug":17,"type":15},{"name":1188,"slug":1189,"type":15},{"slug":1192,"name":1192,"fn":1193,"description":1194,"org":1279,"tags":1280,"stars":27,"repoUrl":28,"updatedAt":1200},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1281,1282,1283],{"name":25,"slug":26,"type":15},{"name":1127,"slug":1128,"type":15},{"name":1158,"slug":1159,"type":15},{"slug":1285,"name":1285,"fn":1286,"description":1287,"org":1288,"tags":1289,"stars":27,"repoUrl":28,"updatedAt":1296},"hf-mcp","access Hugging Face Hub via MCP","Use Hugging Face Hub via MCP server tools. Search models, datasets, Spaces, papers. Get repo details, fetch documentation, run compute jobs, and use Gradio Spaces as AI tools. Available when connected to the HF MCP server.",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1290,1291,1292,1293],{"name":1115,"slug":1116,"type":15},{"name":9,"slug":17,"type":15},{"name":19,"slug":20,"type":15},{"name":1294,"slug":1295,"type":15},"MCP","mcp","2026-04-06T18:25:50.364185",{"slug":4,"name":4,"fn":5,"description":6,"org":1298,"tags":1299,"stars":27,"repoUrl":28,"updatedAt":29},{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1300,1301,1302,1303,1304],{"name":25,"slug":26,"type":15},{"name":22,"slug":23,"type":15},{"name":9,"slug":17,"type":15},{"name":19,"slug":20,"type":15},{"name":13,"slug":14,"type":15},{"slug":1306,"name":1306,"fn":1307,"description":1308,"org":1309,"tags":1310,"stars":27,"repoUrl":28,"updatedAt":1319},"huggingface-best","find and compare Hugging Face models","Use when the user asks about finding the best, top, or recommended model for a task, wants to know what AI model to use, or wants to compare models by benchmark scores. Triggers on: \"best model for X\", \"what model should I use for\", \"top models for [task]\", \"which model runs on my laptop\u002Fmachine\u002Fdevice\", \"recommend a model for\", \"what LLM should I use for\", \"compare models for\", \"what's state of the art for\", or any question about choosing an AI model for a specific use case. Always use this skill when the user wants model recommendations or comparisons, even if they don't explicitly mention HuggingFace or benchmarks.\n",{"slug":8,"name":9,"logoUrl":10,"githubOrg":8},[1311,1314,1315,1316],{"name":1312,"slug":1313,"type":15},"Analytics","analytics",{"name":9,"slug":17,"type":15},{"name":19,"slug":20,"type":15},{"name":1317,"slug":1318,"type":15},"Research","research","2026-04-24T05:09:45.870658",37]