Edit Models filters

Model Tree

Apps

Docker Model Runner

Inference Providers

OVHcloud AI Endpoints

HF Inference API

Misc

Inference Endpoints

text-generation-inference

Eval Results (legacy)

text-embeddings-inference

4-bit precision

8-bit precision

Mixture of Experts

Carbon Emissions

Models

131

Base only

Active filters: mxfp8

MiniMaxAI/MiniMax-M3-MXFP8

Image-Text-to-Text • 440B • Updated 10 days ago • 425k • 41

Winnougan/LTX-2.3-INT8

Updated 2 days ago • 11

TheCluster/Qwen3.5-9B-Claude-4.6-HighIQ-INSTRUCT-HERETIC-UNCENSORED-MLX-mxfp8

Image-Text-to-Text • 9B • Updated Apr 25 • 14.9k • 31

AEON-7/Gemma-4-12B-it-AEON-Abliterated-MLX-8bit

Image-Text-to-Text • 4B • Updated 4 days ago • 4.25k • 3

mlx-community/gemma-4-26B-A4B-it-qat-assistant-mxfp8

Text Generation • 0.1B • Updated 19 days ago • 715 • 1

bsisduck/North-Mini-Code-1.0-MLX-MXFP8

Text Generation • 30B • Updated 15 days ago • 447 • 2

morriszjm/MiniMax-M3-MXFP8-64e

Image-Text-to-Text • 227B • Updated 6 days ago • 16 • 1

nightmedia/gemma-4-12B-coder-fable5-composer2.5-v1-mxfp8-mlx

Any-to-Any • 3B • Updated 2 days ago • 416 • 1

nightmedia/gemma-4-12B-coder-fable5-composer2.5-v1-uncensored-heretic-mxfp8-mlx

Any-to-Any • 3B • Updated 2 days ago • 914 • 1

LibraxisAI/Qwen3-VL-235B-A22B-Instruct-mlx-mxfp8

Image-Text-to-Text • 67B • Updated May 11 • 237 • 1

nightmedia/Qwen3-MOE-4x8B-Janus-Blossom-Claude-Gemini-mxfp8-mlx

Text Generation • 24B • Updated Jan 31 • 38

Foxtr0t/Ministral-3-14B-Reasoning-2512-mlx-mxfp8

4B • Updated Feb 8 • 28

vincentzed-hf/Kimi-K2.5-MXFP8

Image-Text-to-Text • 1T • Updated Feb 11 • 4 • 1

TheCluster/GLM-4.6V-Flash-Heretic-MLX-mxfp8

Image-Text-to-Text • 10B • Updated Feb 27 • 31

TheCluster/Qwen3.5-35B-A3B-Heretic-MLX-mxfp8

Image-Text-to-Text • 35B • Updated Apr 17 • 68 • 4

zianglih/Qwen3-30B-A3B-MXFP8

Text Generation • 31B • Updated Mar 2 • 4

zianglih/Qwen3-30B-A3B-Instruct-2507-MXFP8

Text Generation • 31B • Updated Mar 2 • 532

TheCluster/Qwen3.5-9B-Heretic-MLX-mxfp8

Image-Text-to-Text • 9B • Updated Mar 15 • 86 • 2

AxionML/Kimi-K2.5-MXFP8

Image-Text-to-Text • 1T • Updated Mar 3 • 43

zianglih/Qwen2.5-0.5B-Instruct-MXFP8

Text Generation • 0.5B • Updated Mar 4 • 68

TheCluster/Qwen3.5-4B-Heretic-MLX-mxfp8

Image-Text-to-Text • 1B • Updated Mar 5 • 91 • 2

TheCluster/Qwen3.5-27B-Heretic-Text-MLX-mxfp8

Text Generation • 27B • Updated Mar 8 • 14

AITRADER/Jackrong-Qwen3.5-9B-Claude-Reasoning-abliterated-mxfp8-MLX

Text Generation • 3B • Updated Mar 13 • 208 • 2

AITRADER/Jackrong-Qwen3.5-2B-Claude-Reasoning-abliterated-mxfp8-MLX

Text Generation • 0.9B • Updated Mar 13 • 42

AITRADER/Jackrong-Qwen3.5-4B-Claude-Reasoning-abliterated-mxfp8-MLX

Text Generation • 2B • Updated Mar 13 • 81 • 1

zianglih/Qwen3-30B-A3B-MXFP8-last-8-BF16

Text Generation • 31B • Updated Mar 9 • 5

TheCluster/Qwen3.5-9B-Ultra-Heretic-MLX-mxfp8

Image-Text-to-Text • 9B • Updated Mar 17 • 70 • 2

TheCluster/Qwen3.5-40B-Claude-4.5-Opus-High-Reasoning-Thinking-MLX-mxfp8

Image-Text-to-Text • 39B • Updated Mar 16 • 29 • 1

TheCluster/Qwen3.5-40B-Claude-4.6-Opus-Deckard-Heretic-Uncensored-Thinking-MLX-mxfp8

Image-Text-to-Text • 39B • Updated Mar 16 • 233 • 4

wbkou/Qwen3.5-40B-Claude-4.5-Opus-Distilled-MLX-mxfp8

Image-Text-to-Text • 39B • Updated Mar 16 • 17