This model is an int4 model with group_size 128 of Qwen/Qwen3-4B-Thinking-2507 generated by vastai modelzoo. Please follow the license of the original model.

vllm Inference

vllm >= v0.11.0
VVI >= 26.02

bash

vllm serve vastai-ais/Qwen3-4B-Thinking-2507-GPTQ-INT4 \
--tensor-parallel-size 1 \
--max-model-len 65536 \
--reasoning-parser deepseek_r1 \
--served-model-name qwen

bash

curl http://localhost:8000/v1/chat/completions -H "Content-Type: application/json" -d ' {
    "model": "qwen",
    "messages": [
      {"role": "system", "content": "You are a helpful assistant."},
      {"role": "user", "content": "Who are you?"}
    ],
    "max_tokens": 512
  } '