AutomatosX/AX-MiniMax-M3-MLX-AXQ-MXFP4

Model

stars

commits

linked in READMEs

Aug 23, 2026

updated

4-bit

axquant

conversational

custom_code

experimental

minimax

minimax_m3_vl

mlx

moe

mxfp4

not-certified

safetensors

text-generation

Browse cluster: Quantized LLM Model Optimization →

README

AX-MiniMax-M3-MLX-AXQ-MXFP4

Experimental AXQ MXFP4 MLX pack of MiniMaxAI/MiniMax-M3 (BF16 source).

Not certified. Will not be certified in this revision. Stream required. Hobby / curiosity only. Default Hub name has no -MTP.

Language path only. Vision stays BF16.

Item	Status
Convert + `ax_expert_stream.json`	Factory job on `df-macstudio-m2`
Convert git SHA	`2f4e4e49b82463ac9e146090020a9565c8583253`
License	Upstream MiniMax LICENSE copied into the pack

Contributors

AutomatosX

9 commits

Similar repos

AutomatosX/AX-MiniMax-M3-MLX-AXQ-2bit

Model

shared topics

AutomatosX/AX-Kimi-K3-MLX-AXQ-2bit

Model

shared topics

AutomatosX/AX-Qwen3.8-2.4T-A95B-MLX-AXQ-2bit-MTP

Model

shared topics

AutomatosX/AX-DeepSeek-V4-Pro-0813-MLX-AXQ-2bit-MTP

Model

shared topics

AutomatosX/AX-Qwen3-VL-30B-A3B-Instruct-MLX-AXQ-4bit

Model

shared topics

AutomatosX/AX-DeepSeek-V4-Flash-0731-MLX-AXQ-MXFP4

Model

shared topics

AutomatosX/AX-Muse-Glimmer-30B-MLX-AXQ-4bit

Model

shared topics

AutomatosX/AX-Ministral-3-14B-Instruct-2512-MLX-AXQ-4bit

Model

shared topics

Linked in READMEs

defai-digital/axquant

Not another flat 4-bit quantizer. AXQuant mixes precision layer by layer for Apple Silicon—smaller…

README badge

README

AX-MiniMax-M3-MLX-AXQ-MXFP4

Experimental AXQ MXFP4 MLX pack of MiniMaxAI/MiniMax-M3 (BF16 source).

Not certified. Will not be certified in this revision. Stream required. Hobby / curiosity only. Default Hub name has no -MTP.

Language path only. Vision stays BF16.

Item	Status
Convert + `ax_expert_stream.json`	Factory job on `df-macstudio-m2`
Convert git SHA	`2f4e4e49b82463ac9e146090020a9565c8583253`
License	Upstream MiniMax LICENSE copied into the pack