q4-k-m

#q4-k-m

@mylifcc: I'm already running Gemma-4-12b on my Mac. Tech stack: llama.cpp + GGUF Q4_K_M + Metal 32K context, local OpenAI-compatible API. Measured about 36 tok/s, resident RSS about…

X AI KOLs Timeline ↗ · 2026-06-03 Cached

User shares their experience using llama.cpp with the GGUF Q4_K_M quantized version of Gemma-4-12b on a Mac, achieving local inference speed of about 36 tok/s and memory usage of about 10GB.

0 favorites 0 likes

q4-k-m

@mylifcc: I'm already running Gemma-4-12b on my Mac. Tech stack: llama.cpp + GGUF Q4_K_M + Metal 32K context, local OpenAI-compatible API. Measured about 36 tok/s, resident RSS about…

Submit Feedback