Models

mlx-community/DeepSeek-R1-Distill-Qwen-14B-abliterated-v2-Q4-mlx

Text Generation • 2B • Updated Jan 29 • 52 • 2

Ilebro/normistral-11b-warm-Q4-mlx

Text Generation • 2B • Updated Feb 14 • 12 • 1

Ilebro/normistral-11b-warm-Q3-mlx

Text Generation • 1B • Updated Feb 14 • 9 • 1

mlx-community/olmOCR-7B-0225-preview-bf16

Image-to-Text • 8B • Updated Mar 3 • 78 • 4

mlx-community/Qwen2.5-QwQ-35B-Eureka-Cubed-abliterated-uncensored-4bit

Text Generation • 5B • Updated Mar 8 • 53 • 1

KYUNGYONG/Babel-9B-4bit

1B • Updated Mar 9 • 9 • 1

mlx-community/gemma-3-27b-it-8bit

Image-Text-to-Text • Updated Apr 3 • 1.48k • 6

mlx-community/gemma-3-27b-it-bf16

Image-Text-to-Text • Updated Mar 19 • 1.17k • 3

ds4sd/SmolDocling-256M-preview-mlx-bf16

Image-Text-to-Text • 0.3B • Updated May 22 • 1.93k • 62

mlx-community/Mistral-Small-3.1-24B-Instruct-2503-4bit

Updated Mar 19 • 1.17k • 9

mlx-community/orpheus-3b-0.1-ft-4bit

Text-to-Speech • 0.5B • Updated Mar 21 • 79 • 3

mlx-community/DeepSeek-V3-0324-4bit

Text Generation • 105B • Updated 4 days ago • 2.23k • 36

mlx-community/meta-llama-Llama-4-Scout-17B-16E-fp16

Text Generation • 108B • Updated Apr 6 • 1.15k • 3

mlx-community/3b-fr-pretrain-research_release-4bit

Text-to-Speech • 0.5B • Updated Apr 9 • 5 • 1

mlx-community/3b-hi-ft-research_release-8bit

Text-to-Speech • 0.9B • Updated Apr 9 • 5 • 1

mlx-community/dac-speech-24khz-1.5kbps

Text-to-Speech • 0.1B • Updated Apr 13 • 30 • 1

mlx-community/Dia-1.6B

Text-to-Speech • 2B • Updated Apr 23 • 184 • 22

mlx-community/Qwen3-30B-A3B-4bit-DWQ

Text Generation • 5B • Updated May 5 • 2.7k • 28

mlx-community/Spark-TTS-0.5B-bf16

Text-to-Speech • 0.5B • Updated May 10 • 1.11k • 4

mlx-community/gemma-3-27b-it-4bit-DWQ

Text Generation • 4B • Updated May 14 • 1.15k • 3

Qwen/Qwen3-0.6B-MLX-4bit

Text Generation • 0.1B • Updated 26 days ago • 1.92k • 8

Qwen/Qwen3-0.6B-MLX-bf16

Text Generation • 0.6B • Updated Jul 7 • 1.71k • 5

Qwen/Qwen3-14B-MLX-4bit

Text Generation • 2B • Updated Jul 7 • 234 • 5

mlx-community/QwQ-32b-4bit-DWQ

Text Generation • 5B • Updated May 26 • 35 • 1

mlx-community/Qwen3-Embedding-4B-4bit-DWQ

Feature Extraction • 0.6B • Updated Jun 7 • 2.93k • 5

mlx-community/Qwen3-Embedding-8B-4bit-DWQ

Feature Extraction • 1B • Updated Jun 23 • 2.07k • 4

Qwen/Qwen3-30B-A3B-MLX-4bit

Text Generation • 4B • Updated Jul 7 • 379 • 10

DuckyBlender/brainrot-translator-mlx-8bit

Text Generation • 0.4B • Updated Jul 14 • 14 • 1

mlx-community/Llama-3.2-8X4B-MOE-V2-Dark-Champion-Instruct-uncensored-abliterated-21B-MLX

Text Generation • 21B • Updated Jun 25 • 193 • 1

mlx-community/gemma-3n-E4B-bf16

Image-Text-to-Text • 8B • Updated Jul 12 • 127 • 6