\n
Welcome to the home of exciting quantized models! We'd love to see increased adoption of powerful state-of-the-art open models, and quantization is a key component to make them work on more types of hardware.
\n
Resources:
\n
\n","classNames":"hf-sanitized hf-sanitized-PgSM3YngsuZPvMhicfvTC"},"users":[{"_id":"603d25b75f9d390ab190b777","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1617264212503-603d25b75f9d390ab190b777.jpeg","isPro":false,"fullname":"Pedro Cuenca","user":"pcuenq","type":"user"},{"_id":"60420dccc15e823a685f2b03","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60420dccc15e823a685f2b03/AOApMWt_jvm9e6XQ2vlrJ.jpeg","isPro":true,"fullname":"Daniel Vila","user":"dvilasuero","type":"user"},{"_id":"60f0608166e5701b80ed3f02","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/BHso-wSWpR9b8b8CKvodC.jpeg","isPro":false,"fullname":"Alvaro Bartolome","user":"alvarobartt","type":"user"},{"_id":"61b253b7ac5ecaae3d1efe0c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/61b253b7ac5ecaae3d1efe0c/hwiQ0uvz3t-L5a-NtBIO6.png","isPro":false,"fullname":"Joshua","user":"Xenova","type":"user"},{"_id":"61b85ce86eb1f2c5e6233736","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1655385361868-61b85ce86eb1f2c5e6233736.jpeg","isPro":true,"fullname":"Vaibhav Srivastav","user":"reach-vb","type":"user"},{"_id":"61d2c54d76c37de24cfed058","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1641203017724-noauth.png","isPro":false,"fullname":"Joao Gante","user":"joaogante","type":"user"},{"_id":"6310e9a107a76827902421d7","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6310e9a107a76827902421d7/1e0GItqv3A6sOWYz5SXoe.png","isPro":false,"fullname":"Daniël de Kok","user":"danieldk","type":"user"},{"_id":"63ce875d199b36f7552d4f07","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63ce875d199b36f7552d4f07/bpUrvhXDagzRqZ3vxTcSF.jpeg","isPro":false,"fullname":"Marc Sun","user":"marcsun13","type":"user"},{"_id":"6400f6cc2b67d27affcfdb93","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6400f6cc2b67d27affcfdb93/WA6FEZy_YaZPGhIWj2zda.jpeg","isPro":true,"fullname":"Matthew Douglas","user":"mdouglas","type":"user"},{"_id":"6632d7e22c4f4bfc3f6a05c2","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6632d7e22c4f4bfc3f6a05c2/TCDlrb-O5aormNjSX-tyE.png","isPro":false,"fullname":"Mohamed Mekkouri","user":"medmekk","type":"user"}],"userCount":10,"collections":[{"slug":"hugging-quants/gemma2-awq-quants-6710cb8caa5c3585cb49ad24","title":"Gemma2 AWQ Quants","description":"Optimised AWQ Quants for high-throughput deployments of Gemma2! Compatible with Transformers, TGI & VLLM 🤗","gating":false,"lastUpdated":"2024-10-17T08:32:58.045Z","owner":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"items":[{"_id":"6710cbba2f2350276f3d7d4c","position":0,"type":"model","author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":2096,"gated":false,"id":"hugging-quants/gemma-2-9b-it-AWQ-INT4","availableInferenceProviders":[],"lastModified":"2024-10-17T08:31:37.000Z","likes":6,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":2031715840}],"position":0,"theme":"orange","private":false,"shareUrl":"https://huggingface.co/collections/hugging-quants/gemma2-awq-quants-6710cb8caa5c3585cb49ad24","upvotes":0,"isUpvotedByUser":false},{"slug":"hugging-quants/llama-32-3b-and-1b-gguf-quants-66f43204a559009763c009a5","title":"Llama 3.2 3B & 1B GGUF Quants","description":"Llama.cpp compatible quants for Llama 3.2 3B and 1B Instruct models.","gating":false,"lastUpdated":"2024-09-26T09:27:24.772Z","owner":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"items":[{"_id":"66f4323a4bfac05e4561af58","position":0,"type":"model","author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":2327,"gated":false,"id":"hugging-quants/Llama-3.2-3B-Instruct-Q8_0-GGUF","availableInferenceProviders":[],"lastModified":"2024-09-25T16:11:19.000Z","likes":52,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":3212749888},{"_id":"66f43251ed02030ede899add","position":1,"type":"model","author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":31202,"gated":false,"id":"hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF","availableInferenceProviders":[],"lastModified":"2024-09-25T16:12:08.000Z","likes":20,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":3212749888},{"_id":"66f4324758df8addbc6ad7b1","position":2,"type":"model","author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":20955,"gated":false,"id":"hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF","availableInferenceProviders":[],"lastModified":"2024-09-25T16:14:40.000Z","likes":35,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":1235814432},{"_id":"66f4325a2d7c50d9635a9ff5","position":3,"type":"model","author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":38561,"gated":false,"id":"hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF","availableInferenceProviders":[],"lastModified":"2024-09-25T16:15:26.000Z","likes":17,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":1235814432}],"position":1,"theme":"pink","private":false,"shareUrl":"https://huggingface.co/collections/hugging-quants/llama-32-3b-and-1b-gguf-quants-66f43204a559009763c009a5","upvotes":46,"isUpvotedByUser":false},{"slug":"hugging-quants/llama-31-gptq-awq-and-bnb-quants-669fa7f50f6e713fd54bd198","title":"Llama 3.1 GPTQ, AWQ, and BNB Quants","description":"Optimised Quants for high-throughput deployments! Compatible with Transformers, TGI & VLLM 🤗","gating":false,"lastUpdated":"2024-09-26T09:27:24.764Z","owner":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"items":[{"_id":"669fa8703b600571748e470f","position":0,"type":"model","author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":1312,"gated":false,"id":"hugging-quants/Meta-Llama-3.1-405B-Instruct-AWQ-INT4","availableInferenceProviders":[],"lastModified":"2024-09-13T06:37:37.000Z","likes":36,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":58508394496},{"_id":"66a0ee67c8be189aea2ba207","position":1,"type":"model","author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":9,"gated":false,"id":"hugging-quants/Meta-Llama-3.1-405B-Instruct-BNB-NF4","availableInferenceProviders":[],"lastModified":"2024-09-16T23:46:54.000Z","likes":5,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":213510996356},{"_id":"669fa87993fdcfcb30ad4dd5","position":2,"type":"model","author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":2275,"gated":false,"id":"hugging-quants/Meta-Llama-3.1-405B-Instruct-GPTQ-INT4","availableInferenceProviders":[],"lastModified":"2024-08-07T07:28:07.000Z","likes":16,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":58547617792},{"_id":"669fa886ea38f3fcba4091fb","position":4,"type":"model","author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":394622,"gated":false,"id":"hugging-quants/Meta-Llama-3.1-70B-Instruct-AWQ-INT4","availableInferenceProviders":[],"lastModified":"2024-08-07T07:16:54.000Z","likes":105,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":11260665856}],"position":2,"theme":"orange","private":false,"shareUrl":"https://huggingface.co/collections/hugging-quants/llama-31-gptq-awq-and-bnb-quants-669fa7f50f6e713fd54bd198","upvotes":56,"isUpvotedByUser":false}],"datasets":[],"models":[{"author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":812,"gated":false,"id":"hugging-quants/Llama-4-Scout-17B-16E-Instruct-fbgemm","availableInferenceProviders":[],"lastModified":"2025-04-09T10:57:10.000Z","likes":2,"pipeline_tag":"image-text-to-text","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":108659931392},{"author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":9,"gated":false,"id":"hugging-quants/Llama-4-Scout-17B-16E-Instruct-fbgemm-unfused","availableInferenceProviders":[],"lastModified":"2025-04-09T08:57:23.000Z","likes":2,"pipeline_tag":"image-text-to-text","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":108659931392},{"author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":2096,"gated":false,"id":"hugging-quants/gemma-2-9b-it-AWQ-INT4","availableInferenceProviders":[],"lastModified":"2024-10-17T08:31:37.000Z","likes":6,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":2031715840},{"author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":9533,"gated":false,"id":"hugging-quants/Mixtral-8x7B-Instruct-v0.1-AWQ-INT4","availableInferenceProviders":[],"lastModified":"2024-10-07T06:59:00.000Z","likes":0,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"numParameters":6476533760},{"author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":38561,"gated":false,"id":"hugging-quants/Llama-3.2-1B-Instruct-Q4_K_M-GGUF","availableInferenceProviders":[],"lastModified":"2024-09-25T16:15:26.000Z","likes":17,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":1235814432},{"author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":20955,"gated":false,"id":"hugging-quants/Llama-3.2-1B-Instruct-Q8_0-GGUF","availableInferenceProviders":[],"lastModified":"2024-09-25T16:14:40.000Z","likes":35,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":1235814432},{"author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":31202,"gated":false,"id":"hugging-quants/Llama-3.2-3B-Instruct-Q4_K_M-GGUF","availableInferenceProviders":[],"lastModified":"2024-09-25T16:12:08.000Z","likes":20,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":3212749888},{"author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":2327,"gated":false,"id":"hugging-quants/Llama-3.2-3B-Instruct-Q8_0-GGUF","availableInferenceProviders":[],"lastModified":"2024-09-25T16:11:19.000Z","likes":52,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":3212749888},{"author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":25,"gated":false,"id":"hugging-quants/Meta-Llama-3.1-405B-BNB-NF4","availableInferenceProviders":[],"lastModified":"2024-09-16T23:55:41.000Z","likes":2,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":211330748786},{"author":"hugging-quants","authorData":{"_id":"66978677ebf473b4a901c289","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60f0608166e5701b80ed3f02/Mm_zQGapvXKw4VCCJ8Jbc.png","fullname":"Hugging Quants","name":"hugging-quants","type":"org","isHf":false,"isHfAdmin":false,"isMod":false,"isEnterprise":false,"followerCount":242},"downloads":9,"gated":false,"id":"hugging-quants/Meta-Llama-3.1-405B-Instruct-BNB-NF4","availableInferenceProviders":[],"lastModified":"2024-09-16T23:46:54.000Z","likes":5,"pipeline_tag":"text-generation","private":false,"repoType":"model","isLikedByUser":false,"widgetOutputUrls":[],"numParameters":213510996356}],"spaces":[],"numDatasets":0,"numModels":21,"numSpaces":1,"lastOrgActivities":[],"acceptLanguages":["*"],"canReadRepos":false,"canReadSpaces":false,"blogPosts":[],"currentRepoPage":0,"filters":{}}">
Welcome to the home of exciting quantized models! We'd love to see increased adoption of powerful state-of-the-art open models, and quantization is a key component to make them work on more types of hardware.
Resources: