Benchmark result
qwen3.8-flash-next-sync-s on AMD Radeon RX 7800 XT — 42.7 tok/s
Measured with sync-strata manual on November 19, 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
1st fastest of 2 runs of this model on AMD Radeon RX 7800 XT · median 41.1 tok/s.
sort
- 142.7tok/s51.5sync-stratathis run
- 239.4tok/s67.3sync-strata
Reproduce this run
toolsync-strata manual
modelqwen3.8-flash-next-sync-s
context8,192
thinkingoff
clientv0.4.99+102
Set those in sync-strata, then:
llm-benchmark benchmark --model "qwen3.8-flash-next-sync-s" --tool "sync-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.