mlx-community/DeepSeek-V4-Flash-2bit-DQ
Text Generation • 284B • Updated • 44.6k • 44
holotherapper PRO
holotherapper
AI & ML interests
None yet
Recent Activity
posted an update 15 days ago
Built a CLI called lmm that uses HF Hub Cache as a single model store and symlinks into LM Studio, Jan, etc. so you don't end up with models scattered across different tool directories.
```
brew tap holotherapper/tap && brew install lmm
```
https://github.com/holotherapper/lmm liked a model 29 days ago
mlx-community/DeepSeek-V4-Flash-2bit-DQ liked a model 29 days ago
dealignai/MiniMax-M2.7-JANGTQ-CRACKOrganizations
None yet
liked 2
models 29 days ago
