Benchmark result
Qwen/Qwen2.5-3B-Instruct on AMD Radeon RX 7800 XT — 74.3 tok/s
Measured with vLLM on October 17, 2026.
What the model built
Open full screen →The coding scenario asks for a playable game in a single HTML file. This is exactly what the model returned, unedited; the frame only adds a line that tells this page how tall it is.
How this run compares
Qwen/Qwen2.5-3B-Instruct on other hardware
Reproduce this run
toolvLLM
modelQwen/Qwen2.5-3B-Instruct
context32,768
clientv0.4.96+102
Set those in vLLM, then:
llm-benchmark benchmark --model "Qwen/Qwen2.5-3B-Instruct" --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.