#!/bin/bash

model_postfix="Q8_0"
model_addr="unsloth/gemma-4-12b-it-GGUF"
draft_mtp=""
quant=$1
cache_type="q8_0"
fa="on"

if [[ ${quant} = "q4_xl" ]]; then
  model_postfix="UD-Q4_K_XL"
  cache_type="q4_0"
  model_addr="unsloth/gemma-4-12B-it-qat-GGUF"
  draft_mtp="--spec-type draft-mtp --spec-draft-n-max 4"
elif [[ ${quant} = "q4" ]]; then
  model_postfix="Q4_K_M"
  cache_type="q4_0"
  model_addr="unsloth/gemma-4-12B-it-GGUF"
elif [[ ${quant} = "q5" ]]; then
  model_postfix="Q5_K_M"
  cache_type="q5_0"
elif [[ ${quant} = "q8_small" ]]; then
  model_postfix="Q8_0"
  model_addr="unsloth/gemma-4-E4B-it-GGUF"
  cache_type="q8_0"
  fa="on"
elif [[ ${quant} = "q4_small" ]]; then
  model_postfix="Q4_K_M"
  model_addr="unsloth/gemma-4-E4B-it-GGUF"
  cache_type="q4_0"
  fa="on"
elif [[ ${quant} = "q8_e2b" ]]; then
  model_postfix="Q8_0"
  model_addr="unsloth/gemma-4-E2B-it-GGUF"
  cache_type="q8_0"
  fa="on"
fi

echo "cache_type:${cache_type}; model_postfix:${model_postfix}; draft_mtp:${draft_mtp}"

llama-server \
  -hf ${model_addr}:${model_postfix} \
  --ctx-size 131072 \
  --alias gemma-4 \
  --jinja \
  ${draft_mtp} \
  -ngl 999 \
  -fa ${fa} \
  -b 1024 \
  -ub 512 \
  --no-ui \
  --kv-unified \
  --cache-type-k ${cache_type} \
  --cache-type-v ${cache_type} \
  --repeat-penalty 1.05 \
  --host 0.0.0.0