Benchmark result
qwen3.8-27b-Swift1.5-Uncensored-ATX-AI3 on NVIDIA GeForce RTX 3080 Ti — 90.9 tok/s
Measured with OpenAI-compatible manual on November 22, 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
2nd fastest of 5 runs of this model on NVIDIA GeForce RTX 3080 Ti · median 88.7 tok/s.
sort
- 191.8tok/s84.9OpenAI-compatible
- 290.9tok/s79.9OpenAI-compatiblethis run
- 388.7tok/s83.9llama.cpp
- 485.9tok/s87.8llama.cpp
- 581.8tok/s84.9llama.cpp
Reproduce this run
toolOpenAI-compatible manual
modelqwen3.8-27b-Swift1.5-Uncensored-ATX-AI3
context65,536
clientv0.4.99+102
Set those in OpenAI-compatible, then:
llm-benchmark benchmark --model "qwen3.8-27b-Swift1.5-Uncensored-ATX-AI3" --tool "OpenAI-compatible"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.