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

Model

0

stars

6

commits

1

linked in READMEs

Aug 23, 2026

updated

2-bit

axquant

conversational

custom_code

experimental

minimax

minimax_m3_vl

mlx

moe

not-certified

safetensors

text-generation

README

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

Experimental AXQ 2-bit MLX pack of MiniMaxAI/MiniMax-M3 (BF16 source).

Not certified. Will not be certified in this revision. Layer-stack SSD expert paging is too slow for practical serving. Hobby / curiosity only. No AXQ 4-bit affine sibling. An MXFP4 SKU is a separate pack. Config num_mtp_modules is not packaged MTP, so this leaf has no -MTP.

Language path only. Vision stays BF16; vision generate is not claimed. Quality vs BF16 was not measured.

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
Stream	`--expert-stream required`

Contributors

6 commits

Similar repos

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

0

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

0

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

1

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

0

AutomatosX/AX-gpt-oss-120b-MLX-AXQ-6bit

0

AutomatosX/AX-DeepSeek-V4-Flash-0731-MLX-AXQ-2bit-MTP

0

AutomatosX/AX-Qwen3-VL-30B-A3B-Instruct-MLX-AXQ-6bit

0

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

0

Linked in READMEs

defai-digital/axquant

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

1

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

Model

0

stars

6

commits

1

linked in READMEs

Aug 23, 2026

updated

2-bit

axquant

conversational

custom_code

experimental

minimax

minimax_m3_vl

mlx

moe

not-certified

safetensors

text-generation

README

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

Experimental AXQ 2-bit MLX pack of MiniMaxAI/MiniMax-M3 (BF16 source).

Not certified. Will not be certified in this revision. Layer-stack SSD expert paging is too slow for practical serving. Hobby / curiosity only. No AXQ 4-bit affine sibling. An MXFP4 SKU is a separate pack. Config num_mtp_modules is not packaged MTP, so this leaf has no -MTP.

Language path only. Vision stays BF16; vision generate is not claimed. Quality vs BF16 was not measured.

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
Stream	`--expert-stream required`

Similar repos

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

0

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

0

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

1

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

0

AutomatosX/AX-gpt-oss-120b-MLX-AXQ-6bit

0

AutomatosX/AX-DeepSeek-V4-Flash-0731-MLX-AXQ-2bit-MTP

0

AutomatosX/AX-Qwen3-VL-30B-A3B-Instruct-MLX-AXQ-6bit

0

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

0

Linked in READMEs

defai-digital/axquant

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

1

Contributors

6 commits