Some initial results comparing size and perplexity
#1
by
ubergarm
- opened
I cooked some quants from this using ik_llama.cpp and wrote up my initial observations: https://github.com/ikawrakow/ik_llama.cpp/discussions/334
Two ik_llama.cpp fork quants available here: https://huggingface.co/ubergarm/gemma-3-27b-it-qat-GGUF