nightmedia
/

Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-III-mxfp4-mlx

Text Generation

code generation

Mixture of Experts

Qwen3-Coder-30B-A3B-Instruct

mixture of experts

8 active experts

1 million context

optional thinking

4-bit precision

Model card Files Files and versions

Qwen3-Yoyo-V3-42B-A3B-Thinking-TOTAL-RECALL-ST-TNG-III-mxfp4-mlx

File size: 135 Bytes

ccebe1d

version https://git-lfs.github.com/spec/v1
oid sha256:8866ffb2843287655b62ff5caf7f6f91811e39e9fb438abc8289d123df91aa0c
size 5298895020