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

Model

stars

commits

linked in READMEs

Aug 16, 2026

updated

apple-silicon

axq

axquant

deepseek

mlx

mxfp4

quantized

text-generation

Browse cluster: Model Compression for Edge AI →

README

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

AXQuant MXFP4 pack of DeepSeek-V4-Flash-0731 (--q-mode mxfp4). Recipe examples/deepseek-v4-experimental-mxfp4-v0.1.yaml.

Checkpoint Tier 1 is not certified on df-macstudio-m2 (192 GB). If the pack is in the 170 GB+ class, factory generate/cert is memory-blocked.

This is an MLX Apple MXFP4 pack, not an OCP or NVIDIA checkpoint.

Contributors

AutomatosX

2 commits

Similar repos

AutomatosX/AX-DeepSeek-V4-Flash-0731-MLX-AXQ-6bit

Model

shared topics

AutomatosX/AX-DeepSeek-V4-Flash-0731-MLX-AXQ-4bit-MTP

Model

shared topics

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

Model

shared topics

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

Model

shared topics

AutomatosX/AX-Qwen3-Coder-Next-MLX-AXQ-MXFP4

Model

shared topics

AutomatosX/AX-gpt-oss-20b-MLX-AXQ-4bit

Model

shared topics

AutomatosX/AX-Qwen3.6-27B-MLX-AXQ-4bit

Model

shared topics

AutomatosX/AX-Qwen3.8-27B-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-DeepSeek-V4-Flash-0731-MLX-AXQ-MXFP4

AXQuant MXFP4 pack of DeepSeek-V4-Flash-0731 (--q-mode mxfp4). Recipe examples/deepseek-v4-experimental-mxfp4-v0.1.yaml.

Checkpoint Tier 1 is not certified on df-macstudio-m2 (192 GB). If the pack is in the 170 GB+ class, factory generate/cert is memory-blocked.

This is an MLX Apple MXFP4 pack, not an OCP or NVIDIA checkpoint.