inferencerlabs
/

DeepSeek-V3.2-Speciale-MLX-4.8bit

Text Generation

4-bit precision

Model card Files Files and versions

DeepSeek-V3.2-Speciale-MLX-4.8bit / model-00040-of-00041.safetensors

inferencerlabs's picture

Upload complete model

4607601 verified 28 days ago

history blame contribute delete

10.5 GB

This file is stored with Xet . It is too big to display, but you can still download it.

Large File Pointer Details

( Raw pointer file )

SHA256:: 77554406d99fe5ba13ce3f4a3979fb6f2f41633a8c2b52effafee6392b1b150d
Pointer size:: 136 Bytes
Size of remote file:: 10.5 GB
Xet hash:: a30f96dd5fd6643974c186ca2556a6b8c3fca9a4485060f50da0f3dd3abfe211

Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.