Files
amd-strix-halo-vllm-toolboxes/benchmarks/benchmark_results/btbtyler09_Qwen3-Coder-30B-A3B-Instruct-gptq-4bit_cluster_tp2_eth_throughput.json
2026-02-23 19:39:19 +00:00

7 line
191 B
JSON

{
"elapsed_time": 456.08530166203855,
"num_requests": 200,
"total_num_tokens": 146805,
"requests_per_second": 0.4385144604993234,
"tokens_per_second": 321.88057686801585
}