Benchmark result
swift-1.5-iq3_xxs on AMD Radeon RX 9070/9070 XT/9070 GRE — 57.2 tok/s
Measured with Strata v0.2.6 manual on October 27, 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
Reproduce this run
toolStrata v0.2.6 manual
modelswift-1.5-iq3_xxs
context65,536
clientv0.4.98+102
Set those in Strata v0.2.6, then:
llm-benchmark benchmark --model "swift-1.5-iq3_xxs" --tool "Strata v0.2.6"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.