Views
No views yet
vllm serve mgoin/Qwen3-0.6B-MXFP8
python tests/evals/gsm8k/gsm8k_eval.py
Running GSM8K evaluation: 1319 questions, 5-shot
Evaluating: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1319/1319 [00:04<00:00, 305.10it/s]
Results:
Accuracy: 0.389
Invalid responses: 0.001
Total latency: 4.336 s
Questions per second: 304.229
Total output tokens: 130948
Output tokens per second: 30203.298