And vmem use?
ollama 0.6.6 invoked with:
# server
OLLAMA_FLASH_ATTENTION=1 OLLAMA_KV_CACHE_TYPE=q8_0 ollama serve
# client
ollama run --verbose qwen3:30b-a3b
/set parameter num_ctx 32768TY for this.
update: wow, it's quite fast - 70-80t/s on LM Studio with a few other applications using GPU.