# Preset: Qwen3.6-27B AWQ, 128K context, RTX 3090 Ti 24GB
# vLLM interim — Q4 equivalent (not GGUF; use llamacpp for lmstudio GGUF files)
# Usage: ./scripts/switch-model.sh qwen3.6-27b-awq-128k

DATA_ROOT=/data

VLLM_MODEL=Qwen/Qwen3.6-27B-Instruct-AWQ

SERVED_MODEL_NAME=qwen3.6-27b-awq
QUANTIZATION=awq
VLLM_EXTRA_ARGS=--language-model-only --enforce-eager --reasoning-parser qwen3

MAX_MODEL_LEN=131072
MAX_NUM_SEQS=1
GPU_MEMORY_UTILIZATION=0.95
KV_CACHE_DTYPE=fp8

HF_TOKEN=
VLLM_PORT=8000