Open AI models: new and trending on Hugging Face | AIUnzipped

AIUnzippedAI news and analysis

Model Discovery

✨ Model FinderSynced 11/13/2026, 4:30:47 PM

State of AI Models — Weekly Report

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

View report →

16,953 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

qwen3-8b-pmtpNEW

by Polydim-Einsof

🖥️ GPUFP16~20 GB8B params

⬇ 0♥ 0

Otherother

license:other

View on Hugging Face

qwen3-1.7b-pmtpNEW

by Polydim-Einsof

🖥️ GPUFP16~5 GB1.7B params

⬇ 0♥ 0

Otherother

license:other

View on Hugging Face

tiny-Qwen3ForCausalLMNEW

by peft-internal-testing

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Language

View on Hugging Face

bert-base-cased-pos-conll2003NEW

by elsayedissa

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

tiny-Qwen3MoeForCausalLMNEW

by peft-internal-testing

🖥️ GPUFP16

⬇ 0♥ 0text-generation

Language

View on Hugging Face

tiny-Qwen2_5_VLForConditionalGenerationNEW

by peft-internal-testing

🖥️ GPUFP16

⬇ 0♥ 0image-text-to-text

Image

View on Hugging Face

roman-coin-vit-v6NEW

by rez-zed

🖥️ GPUFP16🔒 Gated

⬇ 0♥ 0image-classification

Imageother

license:other

View on Hugging Face

by orgv3400

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

MedAssist-AI-1BNEW

by hariom-peddawad

🖥️ GPUFP16~3 GB1B params

⬇ 0♥ 0text-generation

Languageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

Qwen-Image-LayeredNEW

by qqceqqq

🖥️ GPUFP16

⬇ 0♥ 0image-text-to-image

Imageapache-2.0

license:apache-2.0

View on Hugging Face

PolyLingo-NLLB-LoRANEW

by SultanPrML

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

lm-checkpoints-2026NEW

by hyoungjoon

🖥️ GPUFP16

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

Phi-3.5-mini-instruct-owl_control-gen4-s42NEW

by MohammadGholizadeh

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

Qwen3.8-27B-speculator.dspark-MXFP4A16NEW

by TeenSpirit

🖥️ GPUFP16~65 GB27B params

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

summ_LoRA_weights_test_small_sample_qwenNEW

by Mmelichukwu

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

Qwen3.8-27B-speculator.dspark-NVFP4A16NEW

by TeenSpirit

🖥️ GPUFP16~65 GB27B params

⬇ 0♥ 0

Otherapache-2.0

license:apache-2.0

View on Hugging Face

ovb-i108-b-lr1e-5-r64-2x8-s42_20261109r3NEW

by khazic

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

ovb-i108-a-lr3e-5-r64-2x8-s42_20261109r3NEW

by khazic

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

mariner-swarm-llama-200m-6bNEW

by Calvin-Xu

🖥️ GPUFP16~15 GB6B params

⬇ 0♥ 1

Otherapache-2.0

license:apache-2.0

View on Hugging Face

qwen3.5-0.8b-rag-stage3NEW

by mktktmr

🖥️ GPUFP16~2 GB800M params

⬇ 0♥ 0

Other

View on Hugging Face

hcommit-022956NEW

by victim822872

🖥️ GPUFP16

⬇ 0♥ 0

Other

View on Hugging Face

gemma-e4b-mutation-orders1-2-4-with-empty-21238NEW

by dkingtutcd

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0image-text-to-text

Imageapache-2.0

conversationallicense:apache-2.0

View on Hugging Face

countdown-rl-qwen3-4b-v2-zeroshot-s2-contNEW

by prada5023

🖥️ GPUFP16~10 GB4B params

⬇ 0♥ 0reinforcement-learning

Otherapache-2.0

license:apache-2.0

View on Hugging Face

qwen-2.5-0.5b-hamming-attention-wikitext2NEW

by tahamajs

🖥️ GPUFP16~2 GB500M params

⬇ 0♥ 0

Other

View on Hugging Face