Hugging Face's logo

RESMP-DEV
/
GLM-4.7-Flash-Marlin-MMFP4

Text Generation
Transformers
Safetensors
English
Chinese
glm4_moe_lite
quantized
Mixture of Experts
4-bit precision
GPTQ
MMFP4
glm
metal-marlin
Mixture of Experts
Model card Files
xet
Community
GLM-4.7-Flash-Marlin-MMFP4 / config.json

Commit History

Initial upload: GLM-4.7-Flash MMFP4 quantization (GPTQ + actorder)
ed522a2
verified

Kearm commited on