FP8 quant?
#10
by
Daemontatox
- opened
Is it possible to get the fp8 version of this model similar to the glm 4.6 and qwen coder models?
Daemontatox
changed discussion status to
closed
@Daemontatox we've just uploaded the FP8 variant: https://hf.co/cerebras/GLM-4.5-Air-REAP-82B-A12B-FP8