Benchmark result

Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp on AMD Radeon RX 9070/9070 XT/9070 GRE — 35.0 tok/s

Measured with vLLM on September 8, 2026.

What the model built

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

Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp on other hardware

27.1tok/s84.52× NVIDIA GeForce RTX 5060

Reproduce this run

toolvLLM

modelQwen3.8-27B-GSQ-RCO-IQ3_S-mtp

context131,072

clientv0.4.44+97

Set those in vLLM, then:

llm-benchmark benchmark --model "Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp" --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.