g0chu/

gemma-4-31B-it-qat-q4_0-unquantized-assistant-q8_0-gguf

/home/gochu/workspace/repos/llama.cpp-gemma4-mtp/build/bin/llama-server \
  -m /home/gochu/workspace/models/gguf/gemma/qat/gemma-4-31B_q4_0-it.gguf \
  -md /home/gochu/workspace/models/gguf/gemma/draft/gemma-4-31B-it-qat-q4_0-unquantized-assistant-q8_0.gguf \
  --spec-type draft-mtp \
  --spec-draft-n-max 3 \
  --host 0.0.0.0 \
  --port 8080 \
  -c 128000 \
  -ngl 99 \
  -sm tensor \
  -b 2048 \
  -ub 512 \
  -fa on \
  -np 1 \
  --jinja \
  --chat-template-kwargs '{"enable_thinking":true}'