Benchmark result
halogen-qwen3.8-flash-next on AMD Radeon 8060S — 66.5 tok/s
Measured with halogen manual on November 3, 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.
Reproduce this run
toolhalogen manual
modelhalogen-qwen3.8-flash-next
context65,536
thinkingon
clientv0.4.98+102
Set those in halogen, then:
llm-benchmark benchmark --model "halogen-qwen3.8-flash-next" --tool "halogen"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.