Benchmark result
qwen35_122b on NVIDIA GeForce RTX 3080 — 15.1 tok/s
Measured with LM Studio on August 25, 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; the frame only adds a line that tells this page how tall it is.
How this run compares
5th fastest of 5 runs of this model on NVIDIA GeForce RTX 3080 · median 15.2 tok/s.
sort
- 115.2tok/s60.2LM Studio
- 215.2tok/s74.3LM Studio
- 315.2tok/s76.1LM Studio
- 415.2tok/s49.5LM Studio
- 515.1tok/s73.2LM Studiothis run
Reproduce this run
toolLM Studio
modelqwen35_122b
context8,192
clientv0.4.43+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen35_122b" --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.