I quantized GLM-4.7-PRISM using the same method than Unsloth Dynamics's GLM 4.7. I copied each tensor type from their quantization, and I used the same imatrix. For now there is only UD-Q4_K_XL because the process is not automatized yet, but I will upload the other quants in a few days probably.
- Downloads last month
- 2,702
Hardware compatibility
Log In
to add your hardware
1-bit
2-bit
4-bit
6-bit
8-bit
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
1
Ask for provider support