Benchmark result
qwen3.8-27b-gsq3 on 2× NVIDIA GeForce RTX 5060 — 114.0 tok/s
Measured with capy-flash manual on October 24, 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
4th fastest of 4 runs of this model on 2× NVIDIA GeForce RTX 5060 · Multi-GPU · median 114.3 tok/s.
sort
- 1114.9tok/s83.3capy-flash
- 2114.5tok/s85.2capy-flash
- 3114.0tok/s83.9capy-flash
- 4114.0tok/s83.9capy-flashthis run
Reproduce this run
toolcapy-flash manual
modelqwen3.8-27b-gsq3
context86,016
thinkingon
clientv0.4.97+102
Set those in capy-flash, then:
llm-benchmark benchmark --model "qwen3.8-27b-gsq3" --tool "capy-flash"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.