Downloads · 30 days
7
9% of all-time downloads
isogen/Jan-v1-4B-exl3-8bpw-h8
Jan-v1-4B-exl3-8bpw-h8 is a machine learning model from isogen. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
EXL3 quantization of Jan-v1-4B, 8 bits per weight, including output layers.
Downloads · 30 days
7
9% of all-time downloads
All-time downloads
77
Public
Parameters
2.4B
4.8 GB on disk
Likes
0
Public
Click a slice to open those files.
.safetensors4.8 GB · 100%
How the weights are stored.
I162B · 84%
From the Hugging Face model README
EXL3 quantization of Jan-v1-4B, 8 bits per weight, including output layers.
| Model | Q4 | Q6 | Q8 | FP16 |
|---|---|---|---|---|
| Jan-v1-4B-exl3-4bpw | 82.3 | 79.3 | 78.0 | 78.0 |
| Jan-v1-4B-exl3-6bpw | 78.0 | 76.8 | 77.4 | 76.8 |
| Jan-v1-4B-exl3-8bpw-h8 | 79.9 | 78.7 | 78.0 | 77.4 |