Benchmark result
qwen/qwen3.8-27b on 4× NVIDIA GeForce GTX 1080 Ti — 17.2 tok/s
Measured with LM Studio on November 6, 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 4× NVIDIA GeForce GTX 1080 Ti · Multi-GPU · median 16.6 tok/s.
sort
- 117.2tok/s82.0LM Studio · Q4_K_Mthis run
- 216.1tok/s75.4LM Studio · Q4_K_M
Reproduce this run
toolLM Studio
modelqwen/qwen3.8-27b (Q4_K_M)
context32,768
effortxhigh (model default)
clientv0.4.98+102
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen/qwen3.8-27b" --tool "LM Studio"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.