Open AI models: new and trending on Hugging Face

Model Discovery

✨ Model FinderSynced 11/3/2026, 8:30:48 PM

📊

State of AI Models — Weekly Report

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

View report →

1,164 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

stride-qwen3-1.7b-allref-correctonly-local-positive-20260925

by sandeep123

⚡ CPU/GPU~5 GB1.7B params

⬇ 0♥ 0text-generation

Language

View on Hugging Face

rh-flux.2-klein-9b-fp8-unet

by RunningHubAI

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

qwen3-0.6b-muc4-lora-smoke

by fnl-es

⚡ CPU/GPU~2 GB600M params

⬇ 0♥ 0

Other

View on Hugging Face

sorcery-steel-klein4b

by zadam7

⚡ CPU/GPU~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

AutoGraphR1-musique_hotpotqa_train-llama3.2-3b-instruct-zeroshot

by gzone0111

⚡ CPU/GPU~8 GB3B params

⬇ 0♥ 0

Other

View on Hugging Face

AutoGraphR1-musique_hotpotqa_train-llama3.2-1b-instruct-zeroshot

by gzone0111

⚡ CPU/GPU~3 GB1B params

⬇ 0♥ 0

Other

View on Hugging Face

AutoGraphR1-musique_hotpotqa_train-qwen2.5-7b-instruct-zeroshot

by gzone0111

⚡ CPU/GPU~17 GB7B params

⬇ 0♥ 0

Other

View on Hugging Face

Titanius-1.1-88m-tools-sft-fp16

by NadavSalem

⚡ CPU/GPU~1 GB88M params

⬇ 0♥ 0text-generation

Language

instruction-tuneddataset:synthetic-tool-usedataset:karpathy/climbmix-400b-shuffle

View on Hugging Face

Nemotron-Labs-Diffusion-3B-openvino-int8

by ryugyosoft

⚡ CPU/GPU~8 GB3B params

⬇ 0♥ 0text-generation

Languageother

license:other

View on Hugging Face

rh-f2-klein-9b-lora-2028738069683249153

by RunningHubAI

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

yxz-ideo4-h5-99ffdb9b-s0b

by bimabk

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0

Other

View on Hugging Face

maxrl-no-eos-qwen3-1.7b-compression-bs32-n16-32k-146103-step_60

by hi-todayis-jh

⚡ CPU/GPU~5 GB1.7B params

⬇ 0♥ 0

Other

View on Hugging Face

rh-flux.2-klein-9b-fp8-unet-2068364922425266178

by RunningHubAI

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

Xuwang-Director-1.7B

by nanohana233

⚡ CPU/GPU~5 GB1.7B params

⬇ 0♥ 0

Other

View on Hugging Face

avigpt-250m-instruct

by AvinashRicky

⚡ CPU/GPU~1 GB250M params

⬇ 0♥ 0text-generation

Languageapache-2.0

license:apache-2.0

View on Hugging Face

MamayLM-Gemma-3-4B-IT-ANE-ctx1024

by nktskr

⚡ CPU/GPU~10 GB4B params

⬇ 0♥ 0text-generation

Languagegemma

conversationallicense:gemma

View on Hugging Face

rh-maperson-klein9b-v1-step750-lora

by RunningHubAI

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

rh-f2-klein-9b-lora-2023248884436312066

by RunningHubAI

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

rh-flux2-klein-9b-lora

by RunningHubAI

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

rh-flux.2-klein-9b-fp16-unet

by RunningHubAI

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face

qwen35-9b-hyperproof-dapo-native-reasoning-8k-gradient-output

by kamilburda

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0

Other

View on Hugging Face

yxz-ideo4-a100base-s1-99ffdb9b

by bimabk

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0

Other

View on Hugging Face

sft-5g-rca-qwen3.5-4B

by JesterbeanLTEA

⚡ CPU/GPU~10 GB4B params

⬇ 0♥ 0

Other

View on Hugging Face

rh-wuji-flux2-klein9b-2603-checkpoint

by RunningHubAI

⚡ CPU/GPU~22 GB9B params

⬇ 0♥ 0text-to-image

Image

View on Hugging Face