Will you release q6_k version too?
#1
by
Hoioi
- opened
Could you please release q6_k version too?
The current ggml version is based on this project: https://github.com/li-plus/chatglm.cpp. Supported quantizations are "f32", "f16", "q8_0", "q4_0", "q4_1", "q5_0", "q5_1". q6_k is not available yet.
We are going to upload the rest of quantization versions soon. Stay tuned :)
Thank you so much. I'm waiting for they to add support for other quantizations.
Hoioi
changed discussion status to
closed