Benchmark result
swift-1.5-qwen3.8-flash-next-iq3_s on NVIDIA GeForce RTX 5090 — 310.6 tok/s
Measured with basalt manual on October 25, 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
1st fastest of 2 runs of this model on NVIDIA GeForce RTX 5090 · median 259.0 tok/s.
sort
- 1310.6tok/s86.4basaltthis run
- 2207.5tok/s86.3Strata
Reproduce this run
toolbasalt manual
modelswift-1.5-qwen3.8-flash-next-iq3_s
context65,536
clientv0.4.97+102
Set those in basalt, then:
llm-benchmark benchmark --model "swift-1.5-qwen3.8-flash-next-iq3_s" --tool "basalt"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.