Benchmark result
swift-1.5-iq3_s on NVIDIA GeForce RTX 5090 — 204.7 tok/s
Measured with vLLM on October 23, 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
2nd fastest of 3 runs of this model on NVIDIA GeForce RTX 5090 · median 204.7 tok/s.
sort
- 1215.1tok/s83.3Strata
- 2204.7tok/s86.0vLLMthis run
- 3200.4tok/s58.7Strata
Reproduce this run
toolvLLM
modelswift-1.5-iq3_s
context131,072
clientv0.4.97+102
Set those in vLLM, then:
llm-benchmark benchmark --model "swift-1.5-iq3_s" --tool "vLLM"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.