Downloads · 30 days
21
13% of all-time downloads
Keozon/GLM-4.5-Air-fp8_e4m3-quark-gfx1100
GLM-4.5-Air-fp8_e4m3-quark-gfx1100 is a machine learning model from Keozon. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
This is an AMD Quark-quantized GLM-4.5 Air in fp8. Quantized on and for GFX1100 cards, in this case 2x W7900.
Downloads · 30 days
21
13% of all-time downloads
All-time downloads
157
Public
Parameters
107B
142 GB on disk
Likes
1
Public
Click a slice to open those files.
.safetensors142 GB · 100%
How the weights are stored.
F8_E4M372.1B · 67%
From the Hugging Face model README
This is an AMD Quark-quantized GLM-4.5 Air in fp8. Quantized on and for GFX1100 cards, in this case 2x W7900.
This is my first quantized model and I'm still evaluating. It was calibrated with wikitext; assuming success, a future iteration will be calibrated on other datasets.
Quantized perplexity on wikitext: 4.96421480178833