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

Reserved Hub name. Weights are not uploaded.

The -MTP suffix is reserved because the Flash-0731 2-bit sibling AX-DeepSeek-V4-Flash-0731-MLX-AXQ-2bit-MTP ships mtp.safetensors. This 4-bit repo currently has no model files.

Source: deepseek-ai/DeepSeek-V4-Flash-0731 @ 7872f01b1d1fe23eabc4c98b48bffcef5a386062. Recipe examples/deepseek-v4-experimental-4bit-g128-dwq-v0.1.yaml.

Property	Value
Hub weights	Not uploaded
MTP present	Reserved by name; sidecar not on this repo
MTP acceleration	Not claimed
Checkpoint Tier 1	Not certified

Do not treat local Studio convert notes or eval records as proof this Hub tree is populated.

Downloads last month: -; Downloads are not tracked for this model. How to track

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

Base model

deepseek-ai/DeepSeek-V4-Flash-0731

Quantized

(184)

this model

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

DeepSeek

Collection

DeepSeek V4 Flash AXQ 2/4/6-bit MTP, Flash-0731 2/4-bit MTP plus MXFP4/6-bit stubs, Pro-0813 hobby 2-bit MTP, and DeepSeek-OCR-2. 3-bit withdrawn. • 10 items • Updated 7 days ago