Open AI models: new and trending on Hugging Face

Model Discovery

✨ Model FinderSynced 11/4/2026, 8:30:47 AM

📊

State of AI Models — Weekly Report

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

View report →

3,787 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

trojan-zoo-qwen25-coder-7b-f03-a6-r2

by aisleinc

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0text-generation

Languageapache-2.0

codelicense:apache-2.0

View on Hugging Face

Ouro-1.4B

by anonymous-bird-72

🖥️ GPUFP16~4 GB1.4B params

⬇ 0♥ 0text-generation

Languageapache-2.0

reasoningconversationallicense:apache-2.0

View on Hugging Face

exp-4b-clip01-g180

by llha-dot

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

mistral-7b-sft-beta-a0.1-b0.1-L4-overlap_subsample-l3-e9

by PessimisticDPO

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0

Other

View on Hugging Face

exp-4b-clip06-g190

by llha-dot

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

Ovis-VL-Embedding-9B

by wl1982

🖥️ GPUFP16~22 GB9B params

⬇ 0♥ 0feature-extraction

Embeddingsapache-2.0

license:apache-2.0

View on Hugging Face

Ovis-VL-Embedding-2B

by wl1982

🖥️ GPUFP16~5 GB2B params

⬇ 0♥ 0feature-extraction

Embeddingsapache-2.0

license:apache-2.0

View on Hugging Face

qwen2.5-coder-3b-agent-lora-sft

by AkameV6p5

🖥️ GPUFP16~8 GB3B params

⬇ 0♥ 0

Other

View on Hugging Face

Llama-3.1-Tulu-3-8B-SFT-a0.1-b0.1-L3-l0-e23

by PessimisticDPO

🖥️ GPUFP16~20 GB8B params

⬇ 0♥ 0

Other

View on Hugging Face

mistral-7b-sft-beta-a0.1-b0.1-L4-overlap_subsample-l1-e12

by PessimisticDPO

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0

Other

View on Hugging Face

Llama-3.1-Tulu-3-8B-SFT-a0.1-b0.1-L3-l2-e23

by PessimisticDPO

🖥️ GPUFP16~20 GB8B params

⬇ 0♥ 0

Other

View on Hugging Face

mistral-7b-sft-beta-a0.1-b0.1-L4-overlap_subsample-l2-e12

by PessimisticDPO

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0

Other

View on Hugging Face

qwen2.5-7b-instruct-precision-legal-sft-int4

by wz7475

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0

Other

View on Hugging Face

qwen2.5-7b-instruct-precision-legal-sft-int8

by wz7475

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0

Other

View on Hugging Face

Llama-3.1-Tulu-3-8B-SFT-a0.1-b0.1-L3-l1-e23

by PessimisticDPO

🖥️ GPUFP16~20 GB8B params

⬇ 0♥ 0

Other

View on Hugging Face

mistral-7b-sft-beta-a0.1-b0.1-L4-overlap_subsample-l0-e12

by PessimisticDPO

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0

Other

View on Hugging Face

mistral-7b-sft-beta-a0.1-b0.1-L4-overlap_subsample-l3-e12

by PessimisticDPO

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0

Other

View on Hugging Face

qwen2.5-7b-instruct-precision-legal-sft-fp16

by wz7475

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0

Other

View on Hugging Face

ALFWorld-Qwen3-8B-Adaptive-Random-Each

by wckwan

🖥️ GPUFP16~20 GB8B params

⬇ 0♥ 0text-generation

Languageapache-2.0

license:apache-2.0

View on Hugging Face

visualrl-qwen3vl4b-ppo1-contrastsink-v2-r2-clean

by Miiche

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

qwen3.5-9b-seq-hh-10k

by ConnorYU

🖥️ GPUFP16~22 GB9B params

⬇ 0♥ 0image-text-to-text

Imageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

AdvTG-Llama3-8B-LoRA

by Aviral20

🖥️ GPUFP16~20 GB8B params

⬇ 0♥ 0

Other

View on Hugging Face

qwen3.5-9b-seq-hh-1k

by ConnorYU

🖥️ GPUFP16~22 GB9B params

⬇ 0♥ 0image-text-to-text

Imageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

qwen3.5-9b-seq-hh-100

by ConnorYU

🖥️ GPUFP16~22 GB9B params

⬇ 0♥ 0image-text-to-text

Imageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face