Benchmark result
qwen3.8-27b-gsq3 on 2× NVIDIA GeForce RTX 5060 — 116.0 tok/s
Measured with capy-flash manual on November 15, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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
1st fastest of 5 runs of this model on 2× NVIDIA GeForce RTX 5060 · Multi-GPU · median 114.5 tok/s.
sort
- 1116.0tok/s82.0capy-flashthis run
- 2114.9tok/s83.3capy-flash
- 3114.5tok/s85.2capy-flash
- 4114.0tok/s83.9capy-flash
- 5114.0tok/s83.9capy-flash
Reproduce this run
toolcapy-flash manual
modelqwen3.8-27b-gsq3
context105,472
thinkingon
clientv0.4.99+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.