Benchmark result
swift-1.5-iq2_xs on AMD Radeon RX 7900 XTX — 60.2 tok/s
Measured with Strata Strata 0.1.41 on October 11, 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
5th fastest of 5 runs of this model on AMD Radeon RX 7900 XTX · median 86.1 tok/s.
sort
- 191.4tok/s48.5Strata
- 286.7tok/s81.7Strata
- 386.1tok/s85.7Strata
- 476.4tok/s87.2Strata
- 560.2tok/s85.5Stratathis run
Reproduce this run
toolStrata Strata 0.1.41
modelswift-1.5-iq2_xs
context65,536
thinkingon
effortxhigh
think limitnone
samplingtemperature 1 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 0.5
clientv0.4.87+102
Set those in Strata, then:
llm-benchmark benchmark --model "swift-1.5-iq2_xs" --tool "Strata"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.