Benchmark result
swift-1.5-27b on 2× AMD Radeon AI PRO R9700 — 95.5 tok/s
Measured with radiance manual on November 12, 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
2nd fastest of 2 runs of this model on 2× AMD Radeon AI PRO R9700 · Multi-GPU · median 96.8 tok/s.
sort
- 198.1tok/s85.3radiance
- 295.5tok/s88.7radiancethis run
Reproduce this run
toolradiance manual
modelswift-1.5-27b
context65,536
clientv0.4.99+102
Set those in radiance, then:
llm-benchmark benchmark --model "swift-1.5-27b" --tool "radiance"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.