Open AI models: new and trending on Hugging Face

Model Discovery

✨ Model FinderSynced 11/3/2026, 12:30:47 PM

📊

State of AI Models — Weekly Report

Top download gainers · rising by likes · new CPU-runnable · best by category

View report →

32 results · clear all

All Language Image Audio Video Multimodal Embeddings Other

All 💻 CPU-friendly 🖥️ GPU required ⚡ Either

All GGUF MLX ONNX AWQ GPTQ FP16 TFLite Llamafile

Any ≤4 GB ≤8 GB ≤16 GB ≤32 GB 32 GB+

All 🟢 Open 🔒 Restricted

🤗 Hugging Face 🏴‍☠️ PirateFace only ⚡ Both

qwen-image-2.1-nunchaku-lite-int4-r32

by lite-infer

🖥️ GPUGPTQ

⬇ 2♥ 0text-to-image

Imageother

license:other

View on Hugging Face

qwen-image-2.1-nunchaku-lite-nvfp4-r32

by lite-infer

🖥️ GPUGPTQ

⬇ 2♥ 0text-to-image

Imageother

license:other

View on Hugging Face

Dark-Scarlett-v1.0-31B-FP8mlp-W4attn-multilingual

by Ful3

🖥️ GPUGPTQ~19 GB31B params

⬇ 0♥ 0

Other

multilingual

View on Hugging Face

Dark-Scarlett-v1.0-31B-W4A16-multilingual

by Ful3

🖥️ GPUGPTQ~19 GB31B params

⬇ 0♥ 0

Other

multilingual

View on Hugging Face

Dark-Scarlett-v1.0-31B-hybrid12-multilingual

by Ful3

🖥️ GPUGPTQ~19 GB31B params

⬇ 0♥ 0

Other

multilingual

View on Hugging Face

Qwen-Image-2.1-W4A4-int4

by ModelsLab

🖥️ GPUGPTQ

⬇ 0♥ 2text-to-image

Imageother

license:other

View on Hugging Face

Qwen-Image-2.1-W4A4-nvfp4

by ModelsLab

🖥️ GPUGPTQ

⬇ 0♥ 0text-to-image

Imageother

license:other

View on Hugging Face

24b1051-Midsem-Compression40-Submission01

by ParthivMEV

🖥️ GPUGPTQ

⬇ 0♥ 0

Other

View on Hugging Face

GLM-5.3-NF4I8-GPTQ-H32-g128

by HawkBearPig

🖥️ GPUGPTQ

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

Image-2.1-Turbo-Calibrated-NVFP4

by ProCreations

🖥️ GPUGPTQ

⬇ 0♥ 1text-to-image

Imageother

license:other

View on Hugging Face

Image-2.1-Turbo-Calibrated-FP8

by ProCreations

🖥️ GPUGPTQ

⬇ 0♥ 1text-to-image

Imageother

license:other

View on Hugging Face

Gemma-3-1B-it-GPTQ-a16w4-4k

by florianvoss

🖥️ GPUGPTQ~1 GB1B params

⬇ 0♥ 0text-generation

Languagegemma

license:gemma

View on Hugging Face

LFM2.5-24B-A2B-TT-Mixed-BFP4-BFP8-P150

by Lottolabs

🖥️ GPUGPTQ~15 GB24B params

⬇ 0♥ 0text-generation

Languageother

license:other

View on Hugging Face

shieldgemma-9b-smoothquant-w8a8

by marcusnogueira

🖥️ GPUGPTQ~6 GB9B params

⬇ 0♥ 0

Other

View on Hugging Face

breeze-tts-2-gptq-int4

by WarrenHal

🖥️ GPUGPTQ

⬇ 0♥ 0

Otherother

license:other

View on Hugging Face

Llama-3.1-8B-Instruct-GPTQ-a16w4

by florianvoss

🖥️ GPUGPTQ~5 GB8B params

⬇ 0♥ 0text-generation

Languagellama3.1

license:llama3.1

View on Hugging Face

EdgeRock-4B-GPTQ

by hkust-aaron

🖥️ GPUGPTQ~3 GB4B params

⬇ 0♥ 0text-generation

Languageother

reasoningconversationallicense:other

View on Hugging Face

Fibo-2.0-dev-NVFP4

by BennyDaBall

🖥️ GPUGPTQ

⬇ 0♥ 0text-to-image

Imagecc-by-nc-4.0

license:cc-by-nc-4.0

View on Hugging Face

Fibo-2.0-dev-OrbitQuant-W4A8

by WaveCut

🖥️ GPUGPTQ

⬇ 0♥ 1text-to-image

Imagecc-by-nc-4.0

license:cc-by-nc-4.0

View on Hugging Face

qwen-image-2.1-turbo-nunchaku-lite-int4-r32

by lite-infer

🖥️ GPUGPTQ

⬇ 0♥ 0text-to-image

Imageother

license:other

View on Hugging Face

qwen-image-2.1-turbo-nunchaku-lite-nvfp4-r32

by lite-infer

🖥️ GPUGPTQ

⬇ 0♥ 0text-to-image

Imageother

license:other

View on Hugging Face

NVIDIA-Nemotron-3.5-Bolt-74B-A9B-W4A16-g64-AutoRound-GPTQ

by urakozz

🖥️ GPUGPTQ~45 GB74B params

⬇ 0♥ 0

Other

View on Hugging Face

Nanbeige4.3-33B-Base-W4A16-AutoRound

by stuchapin

🖥️ GPUGPTQ~20 GB33B params

⬇ 0♥ 0text-generation

Languageother

reasoninglicense:other

View on Hugging Face

Nanbeige4.3-33B-Base-W8A16-AutoRound

by stuchapin

🖥️ GPUGPTQ~20 GB33B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face