258 1 week ago

A memory-efficient compressed variant of GLM-4.7-Flash that maintains near-identical performance while being 25% lighter.

ollama run aia/GLM-4.7-Flash-REAP-23B-A3B-GGUF:Q4_K_M

Details

1 week ago

e1ee2562f912 · 14GB ·

deepseek2
·
23B
·
Q4_K_M
[gMASK]<sop>{{ if .System }}<|system|> {{ .System }}{{ end }}{{ if .Prompt }}<|user|> {{ .Prompt }}{
{ "stop": [ "<|user|>" ] }

Readme

No readme