- Q4F : Q4_K feed-forawrd (Q5_1 for ffn_down due to shape constraints)
- Q8A : Q8_0 attention, Q8_0 output, Q8_0 embeds
- Q8SH : Q8_0 shared experts
Readable speeds on a 24GiB GPU + 64GB RAM
Readable speeds on a 24GiB GPU + 64GB RAM
glm-4.5-air-q4f_q8a_q8sh-00001-of-00002.gguf 37 GBglm-4.5-air-q4f_q8a_q8sh-00002-of-00002.gguf 36 GB有文件?提交种子。
提交种子zai-org/GLM-4.5-Air