Top 100
Models ordered by hosted inventory, most hosted files first, then A–Z. Not a popularity chart.
Showing stale catalog ·
| Type | Model | Recorded size | Downloads | Updated |
|---|---|---|---|---|
bigvgan v2 22khz 80band 256xnvidia/bigvgan_v2_22khz_80band_256xContent controls: not assessed.DetailsSee the publisher’s description →Source: nvidia on Hugging Face. File format: PT.
| 3.79 GB | 1,629,010 downloads on Hugging Face | 2024-09-05 | |
DeepSeek R1deepseek-ai/DeepSeek-R1Content controls: not assessed.DetailsWhat it does: a chat model for text generation.Source: deepseek-ai on Hugging Face. File format: Safetensors.
| 688.6 GB | 7,476,490 downloads on Hugging Face | 2025-03-27 | |
DeepSeek V3deepseek-ai/DeepSeek-V3Content controls: not assessed.DetailsWhat it does: a chat model for text generation.Source: deepseek-ai on Hugging Face. File format: Safetensors.
| 688.6 GB | 1,131,639 downloads on Hugging Face | 2025-03-27 | |
gte base en v1.5Alibaba-NLP/gte-base-en-v1.5Content controls: not assessed.DetailsWhat it does: an embedding model for comparing sentences for search.Source: Alibaba-NLP on Hugging Face. File format: Safetensors, ONNX.
| Unknown | 513,172 downloads on Hugging Face | 2024-11-15 | |
blip2 opt 2.7BSalesforce/blip2-opt-2.7bContent controls: not assessed.DetailsSee the publisher’s description →Source: Salesforce on Hugging Face. File format: Safetensors, BIN.
| 30.5 GB | 694,569 downloads on Hugging Face | 2025-02-03 | |
blip image captioning largeSalesforce/blip-image-captioning-largeContent controls: not assessed.DetailsSee the publisher’s description →Source: Salesforce on Hugging Face. File format: Safetensors, BIN, H5.
| 5.64 GB | 718,105 downloads on Hugging Face | 2025-02-03 | |
mxbai rerank xsmall v1mixedbread-ai/mxbai-rerank-xsmall-v1Content controls: not assessed.DetailsWhat it does: a model for reordering search results against a query.Source: mixedbread-ai on Hugging Face. File format: Safetensors, ONNX.
| 524.3 MB | 553,557 downloads on Hugging Face | 2025-04-02 | |
openai gptopenai-community/openai-gptContent controls: not assessed.DetailsWhat it does: a model for text generation.Source: openai-community on Hugging Face. File format: Safetensors, BIN, H5.
| 2.03 GB | 243,304 downloads on Hugging Face | 2024-02-19 | |
CLIP ViT B 16 laion2B s34B b88Klaion/CLIP-ViT-B-16-laion2B-s34B-b88KContent controls: not assessed.DetailsSee the publisher’s description →Source: laion on Hugging Face. File format: Safetensors, BIN.
| 1.2 GB | 393,167 downloads on Hugging Face | 2023-04-19 | |
clap htsat unfusedlaion/clap-htsat-unfusedContent controls: not assessed.DetailsWhat it does: an embedding model for turning text into vectors for search.Source: laion on Hugging Face. File format: BIN.
| 617.9 MB | 366,545 downloads on Hugging Face | 2023-04-24 | |
CLIP ViT L 14 laion2B s32B b82Klaion/CLIP-ViT-L-14-laion2B-s32B-b82KContent controls: not assessed.DetailsSee the publisher’s description →Source: laion on Hugging Face. File format: Safetensors, BIN.
| 6.85 GB | 350,419 downloads on Hugging Face | 2024-01-16 | |
CLIP convnext base w laion2B s13B b82K augreglaion/CLIP-convnext_base_w-laion2B-s13B-b82K-augregContent controls: not assessed.DetailsSee the publisher’s description →Source: laion on Hugging Face. File format: Safetensors, BIN.
| 1.49 GB | 556,377 downloads on Hugging Face | 2023-04-18 | |
t5 3Bgoogle-t5/t5-3bContent controls: not assessed.DetailsWhat it does: a model for translating text between languages. A mid-size 3-billion-parameter model.Source: google-t5 on Hugging Face. File format: Safetensors, BIN, H5.
| 34.2 GB | 274,204 downloads on Hugging Face | 2024-01-29 | |
xlm roberta largeFacebookAI/xlm-roberta-largeContent controls: not assessed.DetailsWhat it does: a model for predicting missing words.Source: FacebookAI on Hugging Face. File format: Safetensors, ONNX.
| 11.2 GB | 7,006,693 downloads on Hugging Face | 2024-02-19 | |
gemma 4 31B itgoogle/gemma-4-31B-itContent controls: not assessed.DetailsSee the publisher’s description →Source: google on Hugging Face. File format: Safetensors.
| 62.6 GB | 10,937,003 downloads on Hugging Face | 2026-07-20 | |
bert base german casedgoogle-bert/bert-base-german-casedContent controls: not assessed.DetailsWhat it does: a model for predicting missing words.Source: google-bert on Hugging Face. File format: Safetensors, ONNX, BIN.
| 2.38 GB | 513,403 downloads on Hugging Face | 2024-02-19 | |
Qwen3 Embedding 0.6BQwen/Qwen3-Embedding-0.6BContent controls: not assessed.DetailsWhat it does: an embedding model for turning text into vectors for search. A small 0.6-billion-parameter model.Source: Qwen on Hugging Face. File format: Safetensors.
| 1.21 GB | 10,189,053 downloads on Hugging Face | 2026-04-20 | |
Ornith 1.5 9Bornith-ai/Ornith-1.5-9B-GGUFContent controls: not assessed.DetailsWhat it does: a chat model for text generation. A mid-size 9-billion-parameter model.Source: ornith-ai on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 47.8 GB | 54,860 downloads on Hugging Face | 2026-08-24 | |
Gemma4 12B QAT Uncensored HauhauCS BalancedHauhauCS/Gemma4-12B-QAT-Uncensored-HauhauCS-BalancedContent controls: not assessed.DetailsSee the publisher’s description →Source: HauhauCS on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 7.81 GB | 626,923 downloads on Hugging Face | 2026-06-25 | |
gpt oss 120Bopenai/gpt-oss-120bContent controls: not assessed.DetailsWhat it does: a chat model for text generation. A large 120-billion-parameter model.Source: openai on Hugging Face. File format: BIN, Safetensors.
| 195.8 GB | 4,043,429 downloads on Hugging Face | 2025-08-26 | |
notebooksagents-course/notebooksContent controls: not assessed.DetailsSee the publisher’s description →Source: agents-course on Hugging Face.
| 14.9 MB | 0 downloads on Hugging Face | 2026-04-27 | |
Cobijada Minimax H3 Hybrid Pruned ComfyUIWinnougan/Cobijada_Minimax-H3_Hybrid_Pruned_ComfyUIContent controls: not assessed.DetailsSee the publisher’s description →Source: Winnougan on Hugging Face. File format: Safetensors.
| 73.7 GB | 57,536 downloads on Hugging Face | 2026-09-23 | |
CLM v0.1 8BContrastive-LM/CLM-v0.1-8BContent controls: not assessed.DetailsWhat it does: a model for reordering search results against a query. A mid-size 8-billion-parameter model.Source: Contrastive-LM on Hugging Face. File format: PT.
| 75.8 MB | 0 downloads on Hugging Face | 2026-09-24 | |
Qwen Image 2.1unsloth/Qwen-Image-2.1-GGUFContent controls: not assessed.DetailsWhat it does: a model for making images from text.Source: unsloth on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 64.8 GB | 0 downloads on Hugging Face | 2026-09-22 | |
MiniMax H3 Turbo Loralarryvrh/MiniMax-H3-Turbo-LoraContent controls: not assessed.DetailsSee the publisher’s description →Source: larryvrh on Hugging Face. File format: BIN, Safetensors.
| 112.3 GB | 0 downloads on Hugging Face | 2026-08-08 | |
Ternary Bonsai 2 27B Uncensored HereticOS-Software/Ternary-Bonsai-2-27B-Uncensored-Heretic-GGUFContent controls: not assessed.DetailsWhat it does: a chat model for text generation. A large 27-billion-parameter model with content filters removed.Source: OS-Software on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 14.7 GB | 37,729 downloads on Hugging Face | 2026-09-18 | |
Minimax h3 SingularityWarmBloodAban/Minimax-h3_SingularityContent controls: not assessed.DetailsSee the publisher’s description →Source: WarmBloodAban on Hugging Face. File format: Safetensors.
| 66.8 GB | 0 downloads on Hugging Face | 2026-09-18 | |
Cyber Tiel Coder 35B A3B GGUF MTPpeculiar-ragdoll/Cyber-Tiel-Coder-35B-A3B-GGUF-MTPContent controls: not assessed.DetailsSee the publisher’s description →Source: peculiar-ragdoll on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 227.8 GB | 1,772 downloads on Hugging Face | 2026-09-18 | |
Minimax h3 Turbolightx2v/Minimax-h3-TurboContent controls: not assessed.DetailsSee the publisher’s description →Source: lightx2v on Hugging Face. File format: Safetensors.
| 58.8 GB | 0 downloads on Hugging Face | 2026-09-10 | |
Spark X2.5 4BXHToken/Spark-X2.5-4BContent controls: not assessed.DetailsWhat it does: a chat model for text generation. A mid-size 4-billion-parameter model.Source: XHToken on Hugging Face.
| 8.24 GB | 429 downloads on Hugging Face | 2026-09-15 | |
GLM 5.3 CYBERSECURITY FP8dealignai/GLM-5.3-CYBERSECURITY-FP8Content controls: not assessed.DetailsWhat it does: a chat model for text generation.Source: dealignai on Hugging Face. File format: Safetensors.
| 755.7 GB | 94 downloads on Hugging Face | 2026-09-08 | |
Qwythos 9B Claude Mythos 5 1Mempero-ai/Qwythos-9B-Claude-Mythos-5-1M-GGUFContent controls: not assessed.DetailsSee the publisher’s description →Source: empero-ai on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 96.2 GB | 907,682 downloads on Hugging Face | 2026-07-14 | |
Gemma 4 E4B Uncensored HauhauCS AggressiveHauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-AggressiveContent controls: not assessed.DetailsSee the publisher’s description →Source: HauhauCS on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 61.6 GB | 2,071,465 downloads on Hugging Face | 2026-04-06 | |
Kokoro 82Mhexgrad/Kokoro-82MContent controls: not assessed.DetailsWhat it does: a model for turning text into speech.Source: hexgrad on Hugging Face. File format: PTH, PT.
| 363.3 MB | 15,479,373 downloads on Hugging Face | 2025-04-10 | |
Qwen3.8 Flash Next GSQ RCO CoderISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-Coder-GGUFContent controls: not assessed.DetailsSee the publisher’s description →Source: ISTA-DASLab on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 59.3 GB | 334 downloads on Hugging Face | 2026-09-29 | |
MiniMax H3MiniMaxAI/MiniMax-H3Content controls: not assessed.DetailsSource: MiniMaxAI on Hugging Face. File format: Safetensors.
| 498.5 GB | 4,576,471 downloads on Hugging Face | 2026-08-13 | |
Qwen3.8 27B GSQ RCOISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUFContent controls: not assessed.DetailsSee the publisher’s description →Source: ISTA-DASLab on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 81.4 GB | 143 downloads on Hugging Face | 2026-09-02 | |
Qwen3.8 27B Uncensored HauhauCS Aggressive MTPHauhauCS/Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUFContent controls: not assessed.DetailsSee the publisher’s description →Source: HauhauCS on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 172.5 GB | 0 downloads on Hugging Face | 2026-08-17 | |
Qwen3.8 Flash Next GSQ RCOISTA-DASLab/Qwen3.8-Flash-Next-GSQ-RCO-GGUFContent controls: not assessed.DetailsSee the publisher’s description →Source: ISTA-DASLab on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 294.8 GB | 0 downloads on Hugging Face | 2026-09-29 | |
Qwen3.8 Flash NextQwen/Qwen3.8-Flash-NextContent controls: not assessed.DetailsSee the publisher’s description →Source: Qwen on Hugging Face. File format: Safetensors.
| 360 GB | 706,052 downloads on Hugging Face | 2026-08-27 | |
DeepSeek V3 0324deepseek-ai/DeepSeek-V3-0324Content controls: not assessed.DetailsWhat it does: a chat model for text generation.Source: deepseek-ai on Hugging Face. File format: Safetensors.
| 688.6 GB | 1,171,847 downloads on Hugging Face | 2025-03-27 | |
Wan 2.2 ComfyUI RepackagedComfy-Org/Wan_2.2_ComfyUI_RepackagedContent controls: not assessed.DetailsSee the publisher’s description →Source: Comfy-Org on Hugging Face. File format: Safetensors.
| 728.7 GB | 6,104,835 downloads on Hugging Face | 2026-09-23 | |
Bonsai 27Bprism-ml/Bonsai-27B-ggufContent controls: not assessed.DetailsWhat it does: a chat model for text generation. A large 27-billion-parameter model.Source: prism-ml on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 68.3 GB | 2,455,730 downloads on Hugging Face | 2026-07-17 | |
Qwen Fixed Templatesfroggeric/Qwen-Fixed-Chat-TemplatesContent controls: not assessed.DetailsSee the publisher’s description →Source: froggeric on Hugging Face.
| 1.29 MB | 0 downloads on Hugging Face | 2026-09-04 | |
Qwen3 Coder 30B A3Bunsloth/Qwen3-Coder-30B-A3B-Instruct-GGUFContent controls: not assessed.DetailsWhat it does: a chat model for text generation. A large 30-billion-parameter model.Source: unsloth on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 506.4 GB | 243,253 downloads on Hugging Face | 2026-01-30 | |
gpt oss 20Bopenai/gpt-oss-20bContent controls: not assessed.DetailsWhat it does: a chat model for text generation. A large 20-billion-parameter model.Source: openai on Hugging Face. File format: BIN, Safetensors.
| 41.3 GB | 7,000,889 downloads on Hugging Face | 2025-08-26 | |
Llama xLAM 2 8B fc rSalesforce/Llama-xLAM-2-8b-fc-rContent controls: not assessed.DetailsWhat it does: a chat model for text generation. A mid-size 8-billion-parameter model.Source: Salesforce on Hugging Face. File format: Safetensors.
| 16.1 GB | 32,714 downloads on Hugging Face | 2025-05-06 | |
Qwen3.6 27B Fable Fusion 711 Uncensored Heretic NM DAU NEO MAX MTPDavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUFContent controls: not assessed.DetailsSee the publisher’s description →Source: DavidAU on Hugging Face. File format: GGUF. GGUF files use llama.cpp-compatible runners.
| 465.1 GB | 955,767 downloads on Hugging Face | 2026-09-17 | |
MiMo V2.6 Distill Qwen 9BXiaomiMiMo/MiMo-V2.6-Distill-Qwen-9BContent controls: not assessed.DetailsSee the publisher’s description →Source: XiaomiMiMo on Hugging Face. File format: Safetensors.
| 18.8 GB | 0 downloads on Hugging Face | 2026-09-22 | |
Ming Image 0.1 DesigninclusionAI/Ming-Image-0.1-DesignContent controls: not assessed.DetailsWhat it does: a model for making images from text.Source: inclusionAI on Hugging Face. File format: Safetensors.
| 52.9 GB | 0 downloads on Hugging Face | 2026-09-23 |