Open AI models: new and trending on Hugging Face

Model Discovery

✨ Model FinderSynced 11/4/2026, 12:30:48 AM

📊

State of AI Models — Weekly Report

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

View report →

391 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

LFM2.5-24B-A2B-MLX-Serve-mixed-4-8bit

by pgmharikrishnan

💻 CPUMLX~15 GB24B params

⬇ 0♥ 1text-generation

Languageother

conversationallicense:other

View on Hugging Face

drama-3-mlx-q8

by cguldogan

💻 CPUMLX

⬇ 0♥ 0

Other

View on Hugging Face

drama-3-mlx-q4

by cguldogan

💻 CPUMLX

⬇ 0♥ 0

Other

View on Hugging Face

GLM-OCR-ita-mlx-8bit

by fabriziosalmi

💻 CPUMLX

⬇ 0♥ 0

Other

View on Hugging Face

Qwen3.8-Flash-Next-Uncensored-oQ4e-100K-MTP-plefp8

by zviratko

💻 CPUMLX

⬇ 0♥ 0image-text-to-text

Imageother

conversationallicense:other

View on Hugging Face

Qwen3.8-Flash-Next-MLX-Serve-iQ-MLX-7.1bpw

by xpashkin

💻 CPUMLX

⬇ 0♥ 1text-generation

Languageother

conversationallicense:other

View on Hugging Face

LFM2.5-24B-A2B-EXL3-4bpw

by 0xzknw

💻 CPUMLX~15 GB24B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

Llama-3_3-Nemotron-Super-49B-v1_5-lecore-mlx

by staccs

💻 CPUMLX~30 GB49B params

⬇ 0♥ 0text-generation

Language

conversational

View on Hugging Face

Qwen2.5-72B-Instruct-lecore-mlx

by staccs

💻 CPUMLX~44 GB72B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

personality-interpretation-zh-mlx-4bit

by 6guwew

💻 CPUMLX

⬇ 0♥ 0

Other

View on Hugging Face

Niwaki-Flash-Next-15GB-v5.0-mlx

by neopolita

💻 CPUMLX

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

Qwen3.8-Flash-Next-mixed-iQ5-ple16-mlx-serve

by airagrp

💻 CPUMLX

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-MLX-3bit

by rapid-mlx

💻 CPUMLX~72 GB120B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

LFM2.5-24B-A2B-OptiQ-4bit

by mlx-community

💻 CPUMLX~15 GB24B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

Qwen3.8-Flash-Next-MLX-4bit-ablation

by True2456

💻 CPUMLX

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-MLX-4bit

by rapid-mlx

💻 CPUMLX~72 GB120B params

⬇ 0♥ 0text-generation

Languageother

conversationallicense:other

View on Hugging Face

vism-ai

by ProximaAtlas

💻 CPUMLX

⬇ 0♥ 0text-generation

Languagegemma

conversationallicense:gemma

View on Hugging Face

apertus-v1.5-8b-de-to-zurich-mlx-4bit

by alise441

💻 CPUMLX~5 GB8B params🔒 Gated

⬇ 0♥ 0text-generation

Languagecc-by-nc-4.0

conversationallicense:cc-by-nc-4.0

View on Hugging Face

FLUX.3-Image-Klein-mlx-4bit

by vanch007

💻 CPUMLX

⬇ 0♥ 0text-to-image

Imageother

license:other

View on Hugging Face

FLUX.3-Image-Klein-mlx-8bit

by vanch007

💻 CPUMLX

⬇ 0♥ 0text-to-image

Imageother

license:other

View on Hugging Face

qwen-image-2-1-turbo-mlx

by SceneWorks

💻 CPUMLX

⬇ 0♥ 0text-to-image

Imageother

license:other

View on Hugging Face

NVIDIA-Nemotron-3.5-Super-VL-120B-A12B-LiLiCorr-MLX-BF16

by thelogicalgate

💻 CPUMLX~72 GB120B params

⬇ 0♥ 0

Other

View on Hugging Face

Qwen3.8-27B-USS-Threshold-qx64-hi-mlx

by nightmedia

💻 CPUMLX~17 GB27B params🔒 Gated

⬇ 0♥ 0

Other

View on Hugging Face

clef-oQ2e

by g-oQ

💻 CPUMLX

⬇ 0♥ 0

Other

View on Hugging Face