Open AI models: new and trending on Hugging Face

Model Discovery

✨ Model FinderSynced 11/5/2026, 4:30:47 PM

📊

State of AI Models — Weekly Report

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

View report →

1,325 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

math-tutor-qwen2.5-1.5b-GGUFNEW

by HauHau2010

💻 CPUGGUF~1 GB1.5B params

⬇ 0♥ 0

Other

conversational

View on Hugging Face

LFM2.5-350M-SmolDataEnvs-SFT-adapterNEW

by lugman-madhiai

🖥️ GPUFP16~1 GB350M params

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

gemma-2-2b-it-friendly-ggufNEW

by Displaynamethecat

💻 CPUGGUF~2 GB2B params

⬇ 0♥ 0

Other

conversational

View on Hugging Face

NSFW_Wan_14b-videoNEW

by Richardbosch25

💻 CPUGGUF~9 GB14B params

⬇ 0♥ 1

Othercreativeml-openrail-m

license:creativeml-openrail-m

View on Hugging Face

qwen2.5-0.5b-transcodersNEW

by sackfield

⚡ CPU/GPU~2 GB500M params

⬇ 0♥ 0

Othermit

dataset:neelnanda/pile-10klicense:mit

View on Hugging Face

gemma-4-e2b-it-mobius-int4_rai_1.9.0_m_1.0.1_npuNEW

by amd

⚡ CPU/GPU~5 GB2B params

⬇ 0♥ 0

Other

View on Hugging Face

Qwen3.5-2B-Wolof-Instruct-v1-i1-GGUFNEW

by mradermacher

💻 CPUGGUF~2 GB2B params

⬇ 0♥ 0

Other

View on Hugging Face

LFM2.5-350M-SmolDataEnvs-Easy-Recovery-SFT-r16-a32-lr4e-4-adapterNEW

by lugman-madhiai

🖥️ GPUFP16~1 GB350M params

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

audio8-tts-realistic-0.6b-loomNEW

by loom-ai-org

⚡ CPU/GPU~2 GB600M params

⬇ 0♥ 0

Other

View on Hugging Face

MathQwen_2NEW

by 56m

💻 CPUGGUF~1 GB56M params

⬇ 0♥ 0

Other

conversational

View on Hugging Face

Qwen3.5-08B-Wolof-Instruct-v1-i1-GGUFNEW

by mradermacher

💻 CPUGGUF~5 GB8B params

⬇ 0♥ 0

Other

conversational

View on Hugging Face

Qwen3.8-9B-Distill-china-uncensored-GGUFNEW

by benjamin920101

💻 CPUGGUF~6 GB9B params

⬇ 0♥ 0

Other

View on Hugging Face

Spark-X2.6-4B-abliterated-i1-GGUFNEW

by mradermacher

💻 CPUGGUF~3 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

llama3.2-3b-snli-with-instructions-autoregressive-seed2026NEW

by NexaNLP

🖥️ GPUFP16~8 GB3B params

⬇ 0♥ 0

Other

View on Hugging Face

Qwen-3.5-0.8B-Picture-CaptionerNEW

by agentlans

⚡ CPU/GPU~2 GB800M params

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

Llama-3.2-3B-Instruct_MATH_CODE_BI_AblationNEW

by HoangTran223

⚡ CPU/GPU~8 GB3B params

⬇ 0♥ 0

Other

View on Hugging Face

g56lab-1019-tg1b-281-s5NEW

by Aftian2429

⚡ CPU/GPU~3 GB1B params

⬇ 0♥ 0

Other

View on Hugging Face

gemma3-270m-up6-clean-a0NEW

by AletheiaAING

⚡ CPU/GPU~1 GB270M params

⬇ 0♥ 0

Other

View on Hugging Face

AstrAI-V1-2B-instructNEW

by ViperEkura

🖥️ GPUFP16~5 GB2B params

⬇ 0♥ 0

Other

View on Hugging Face

P220-ThaiOCR-9B-GGUFNEW

by mradermacher

💻 CPUGGUF~6 GB9B params

⬇ 0♥ 0

Other

View on Hugging Face

nobidog-1b-0.2-GGUFNEW

by mradermacher

💻 CPUGGUF~1 GB1B params

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0conversational

View on Hugging Face

gamblerinsight-1b-smokeNEW

by tayaee

🖥️ GPUFP16~3 GB1B params

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

nobidog-qubo-1b-0.2-GGUFNEW

by mradermacher

💻 CPUGGUF~1 GB1B params

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0conversational

View on Hugging Face

openflow-cleanup-qwen2.5-1.5bNEW

by bhullar17noor

💻 CPUGGUF~1 GB1.5B params

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0conversational

View on Hugging Face