Downloads · 30 days
62
7% of all-time downloads
DevQuasar/deepseek-ai.DeepSeek-V3.2-Speciale-Channel-INT8
deepseek-ai.DeepSeek-V3.2-Speciale-Channel-INT8 is a text generation model from DevQuasar. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as mit.
<img src="https://raw.githubusercontent.com/csabakecskemeti/devquasar/main/dqlogoblack-transparent.png" width="200"/
Downloads · 30 days
62
7% of all-time downloads
All-time downloads
892
Public
Parameters
686B
691 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors691 GB · 100%
How the weights are stored.
I8681B · 99%
From the Hugging Face model README
'Make knowledge free for everyone'
Channel wise INT8 quant. Requires CPU with AMX support (Xeon 5 and above) and 700GB-1TB ram. Not tested due to hardware.
SGlang sould support it. SGlang CPU
<a href='https://ko-fi.com/L4L416YX7C' target='_blank'><img height='36' style='border:0px;height:36px;' src='https://storage.ko-fi.com/cdn/kofi6.png?v=6' border='0' alt='Buy Me a Coffee at ko-fi.com' /></a>