varjosoft
/

GLM-4.7-Flash-TQ3

turboquant-vllm

Mixture of Experts

weight-compression

Model card Files Files and versions

GLM-4.7-Flash-TQ3

Commit History

Add model card

2a19f00
verified

varjoranta commited on 7 days ago

TQ3 native checkpoint (3-bit TurboQuant, group_size=128)

3b77a21
verified

varjoranta commited on 7 days ago

initial commit

d074bb0
verified

varjoranta commited on 7 days ago