Benchmark result
qwen/qwen3.5-9b on NVIDIA GeForce RTX 5070 +1 more — 78.6 tok/s
Measured with LM Studio on August 7, 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
1st fastest of 2 runs of this model on NVIDIA GeForce RTX 5070 +1 more · Multi-GPU · median 78.5 tok/s.
sort
- 178.6tok/s70.3LM Studiothis run
- 278.4tok/s74.9LM Studio
Reproduce this run
toolLM Studio
modelqwen/qwen3.5-9b
context16,384
clientv0.4.30+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "qwen/qwen3.5-9b" --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.