Downloads · 30 days
3
1% of all-time downloads
Dark-Nexus-24B-v2.0-AWQ-4bit-g64
tooolz/Dark-Nexus-24B-v2.0-AWQ-4bit-g64
Dark-Nexus-24B-v2.0-AWQ-4bit-g64 is a machine learning model from tooolz. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
https://huggingface.co/ReadyArt/Dark-Nexus-24B-v2.0
All-time downloads
203
Public
Parameters
23.6B
14.7 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.7 GB · 100%
Parameter types
How the weights are stored.
I3222.2B · 94%
Base models
Model card
From the Hugging Face model README
https://huggingface.co/ReadyArt/Dark-Nexus-24B-v2.0
- quantized using AutoAWQ,
- 4bit
- group_size 64
- zero_point: True
- GEMM
this model does not like temps over 0.5 unlike the 12b version.
- Type
- mistral
- Created
- Nov 25, 2025
- Updated
- Nov 25, 2025