AIUnzipped — AI news that makes sense

Model Discovery

Synced 9/18/2026, 8:26:49 PM

228 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

Qwen3.6-27B

by Qwen

🖥️ GPUFP16~65 GB27B params

⬇ 3.6M♥ 2.3Kimage-text-to-text

Imageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

Qwen2.5-7B-Instruct-AWQ

by Qwen

🖥️ GPUAWQ~5 GB7B params

⬇ 3.5M♥ 53text-generation

Languageapache-2.0

chatconversationallicense:apache-2.0

View on Hugging Face

pythia-160m

by EleutherAI

🖥️ GPUFP16~1 GB160M params

⬇ 3.5M♥ 45text-generation

Languageapache-2.0

dataset:eleutherai/pilelicense:apache-2.0

View on Hugging Face

Qwen3.6-35B-A3B

by Qwen

🖥️ GPUFP16~84 GB35B params

⬇ 3.3M♥ 2.8Kimage-text-to-text

Imageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

GLM-5.3-Flash

by zai-org

🖥️ GPUFP16

⬇ 2.9M♥ 2.5Kimage-text-to-text

Imagemit

conversationallicense:mit

View on Hugging Face

Qwen2.5-Coder-7B-Instruct

by Qwen

🖥️ GPUFP16~17 GB7B params

⬇ 2.6M♥ 801text-generation

Languageapache-2.0

codechatconversationallicense:apache-2.0

View on Hugging Face

Qwen3-14B-AWQ

by Qwen

🖥️ GPUAWQ~9 GB14B params

⬇ 2.6M♥ 74text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

DeepSeek-V3.2

by deepseek-ai

🖥️ GPUFP16

⬇ 2.4M♥ 1.5Ktext-generation

Languagemit

license:mit

View on Hugging Face

Mistral-7B-Instruct-v0.3

by mistralai

🖥️ GPUFP16~17 GB7B params

⬇ 2.4M♥ 3.5K

Otherapache-2.0

license:apache-2.0

View on Hugging Face

Qwen2.5-14B-Instruct

by Qwen

🖥️ GPUFP16~34 GB14B params

⬇ 2.4M♥ 368text-generation

Languageapache-2.0

chatconversationallicense:apache-2.0

View on Hugging Face

DeepSeek-OCR

by deepseek-ai

🖥️ GPUFP16

⬇ 2.3M♥ 3.4Kimage-text-to-text

Imagemit

multilinguallicense:mit

View on Hugging Face

Qwen2.5-32B-Instruct

by Qwen

🖥️ GPUFP16~77 GB32B params

⬇ 2.2M♥ 362text-generation

Languageapache-2.0

chatconversationallicense:apache-2.0

View on Hugging Face

Unlimited-OCR

by baidu

🖥️ GPUFP16

⬇ 2.2M♥ 4.3Kimage-text-to-text

Imagemit

multilinguallicense:mit

View on Hugging Face

SmolLM2-135M

by HuggingFaceTB

🖥️ GPUFP16~1 GB135M params

⬇ 2.1M♥ 233text-generation

Languageapache-2.0

license:apache-2.0

View on Hugging Face

Qwen2.5-14B-Instruct-AWQ

by Qwen

🖥️ GPUAWQ~9 GB14B params

⬇ 2.1M♥ 39text-generation

Languageapache-2.0

chatconversationallicense:apache-2.0

View on Hugging Face

Ornith-1.0-35B

by ornith-ai

🖥️ GPUFP16~84 GB35B params

⬇ 2.0M♥ 506text-generation

Languagemit

conversationallicense:mit

View on Hugging Face

Qwen3-14B

by Qwen

🖥️ GPUFP16~34 GB14B params

⬇ 1.9M♥ 474text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

GLM-4.7-Flash

by zai-org

🖥️ GPUFP16

⬇ 1.9M♥ 1.8Ktext-generation

Languagemit

conversationallicense:mit

View on Hugging Face

Qwen2.5-Coder-14B-Instruct

by Qwen

🖥️ GPUFP16~34 GB14B params

⬇ 1.8M♥ 188text-generation

Languageapache-2.0

codechatconversationallicense:apache-2.0

View on Hugging Face

Gemma-4-26B-A4B-NVFP4

by nvidia

🖥️ GPUFP16~63 GB26B params

⬇ 1.8M♥ 147text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

Qwen3-30B-A3B

by Qwen

🖥️ GPUFP16~72 GB30B params

⬇ 1.8M♥ 944text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

stable-diffusion-v1-5

by stable-diffusion-v1-5

🖥️ GPUFP16

⬇ 1.8M♥ 1.3Ktext-to-image

Imagecreativeml-openrail-m

license:creativeml-openrail-m

View on Hugging Face

Qwen3-8B-AWQ

by Qwen

🖥️ GPUAWQ~5 GB8B params

⬇ 1.8M♥ 54text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

Mistral-7B-Instruct-v0.2

by mistralai

🖥️ GPUFP16~17 GB7B params

⬇ 1.8M♥ 3.2Ktext-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face