Search Results
6/29/2025, 9:32:26 PM
>>105746664
>Q8 GGUF is 8 bit floating point
what are you talking about? it's 8.5bpw
https://github.com/ggml-org/llama.cpp/blob/master/tools/quantize/README.md
>Q8 GGUF is 8 bit floating point
what are you talking about? it's 8.5bpw
https://github.com/ggml-org/llama.cpp/blob/master/tools/quantize/README.md
Page 1