Too big
#1
by
ShunAonuma
- opened
Why it's a 9 GB model after 4-bit quantization?
The 4-bit GGUF versions (like Q4_K_M) are about 5 GB.
Why it's a 9 GB model after 4-bit quantization?
The 4-bit GGUF versions (like Q4_K_M) are about 5 GB.