Benchmark result
qwen3.8-27b on 2× AMD Radeon RX 7900 XT/7900 XTX/7900M — 51.9 tok/s
Measured with LM Studio on September 14, 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.
How this run compares
3rd fastest of 5 runs of this model on 2× AMD Radeon RX 7900 XT/7900 XTX/7900M · Multi-GPU · median 51.9 tok/s.
sort
- 152.4tok/s84.4llama.cpp
- 252.0tok/s61.7llama.cpp
- 351.9tok/s86.3LM Studiothis run
- 451.5tok/s44.7llama.cpp
- 551.3tok/s44.6llama.cpp
Reproduce this run
toolLM Studio
modelqwen3.8-27b
context65,536
clientv0.4.59+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "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.