Benchmark result
qwen3.8-27b on NVIDIA GeForce RTX 3090 — 94.9 tok/s
Measured with vLLM manual on October 5, 2026.
How this run compares
Reproduce this run
toolvLLM manual
modelqwen3.8-27b
context8,192
clientv0.4.87+102
Set those in vLLM, then:
llm-benchmark benchmark --model "qwen3.8-27b" --tool "vLLM"The client prompts for context length and thinking mode, and for the KV cache dtype on Unsloth Studio. Sampling is left at the model default — the values above are what the tool reported using, not overrides the client sent.