Hugging Face's logo

varjosoft
/
GLM-4.7-Flash-TQ3

Safetensors
turboquant-vllm
glm4_moe_lite
turboquant
quantization
Mixture of Experts
vllm
weight-compression
3-bit
Model card Files
xet
 Community
GLM-4.7-Flash-TQ3 / tokenizer_config.json

Commit History

TQ3 native checkpoint (3-bit TurboQuant, group_size=128)
3b77a21
verified

varjoranta commited on