Open AI models: new and trending on Hugging Face

Model Discovery

✨ Model FinderSynced 11/4/2026, 8:30:48 PM

📊

State of AI Models — Weekly Report

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

View report →

3,049 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

teja-ai-gemma4-e2b-lora

by Tulasiteja9

🖥️ GPUFP16~5 GB2B params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

qwen3-4b-p2-c0-out160

by joshycodes

⚡ CPU/GPU~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

Babilona-8B-i1-GGUF

by mradermacher

💻 CPUGGUF~5 GB8B params

⬇ 0♥ 0

Other

conversational

View on Hugging Face

Anima2.9b

by copilot-pantry

⚡ CPU/GPU~7 GB2.9B params

⬇ 0♥ 0

Other

View on Hugging Face

qwen3-4b-p2-f3-out160

by joshycodes

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Otherother

license:other

View on Hugging Face

qwen3-4b-p2-f30-out160

by joshycodes

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Otherother

license:other

View on Hugging Face

gemma-4-E2B-it-pi-mono-sft

by sriharsha4444

🖥️ GPUFP16~5 GB2B params

⬇ 0♥ 0text-generation

Languagegemma

conversationaldataset:badlogicgames/pi-monodataset:sriharsha4444/pi-mono-gemma4-sftlicense:gemma

View on Hugging Face

TPAE-D-Qwen2.5-7B

by Zhihan

⚡ CPU/GPU~17 GB7B params

⬇ 0♥ 0

Other

View on Hugging Face

qwen3-4b-rar-medicine-onlinerubrics-seed11-step-046

by HYU-NLP-EVAL

⚡ CPU/GPU~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

Qwen3-0.6B-JSON-SFT

by mgmbykai

🖥️ GPUFP16~2 GB600M params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

Qwen3-0.6B-JSON-SFT

by egoigo

🖥️ GPUFP16~2 GB600M params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

Qwen3-0.6B-JSON-SFT

by kihyun-K

🖥️ GPUFP16~2 GB600M params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

Qwen3-0.6B-JSON-SFT

by luckysong777

🖥️ GPUFP16~2 GB600M params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

Qwen3-0.6B-JSON-SFT

by Taewan123

🖥️ GPUFP16~2 GB600M params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

Qwen3-0.6B-JSON-SFT

by haensumo

🖥️ GPUFP16~2 GB600M params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

Qwen3-0.6B-JSON-SFT

by ohkwon

🖥️ GPUFP16~2 GB600M params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

gemma-4-12B-it-GTAP-v3-GGUF

by DuoNeural

💻 CPUGGUF~8 GB12B params

⬇ 0♥ 0text-generation

Languagegemma

license:gemmaconversational

View on Hugging Face

TPAE-G-Qwen2.5-7B

by Zhihan

🖥️ GPUFP16~17 GB7B params

⬇ 0♥ 0image-text-to-text

Image

conversational

View on Hugging Face

gemma3-1b-given-to-find-formula-distilled_0.1

by CoriolisTechnologies

🖥️ GPUFP16~3 GB1B params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

Qwen3-4B-Base_d2d_antiprefill_masked_n5_r4

by NeelRajani

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

Qwen3-4B-Base_d2d_antiprefill_masked_n5_r2

by NeelRajani

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

l0-qwen3-1.7b-compression-bs32-n16-32k-t1-no-eos-verl091-146102-step_10

by hi-todayis-jh

⚡ CPU/GPU~5 GB1.7B params

⬇ 0♥ 0

Other

View on Hugging Face

Qwen3-4B-Base_d2d_antiprefill_masked_r64

by NeelRajani

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

Qwen3-4B-Base_d2d_antiprefill_masked_r32

by NeelRajani

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face