Benchmark result
unsloth/Qwen3.5-9B-GGUF on Intel(R) Arc(TM) 140V GPU (16GB) — 13.8 tok/s
Measured with Unsloth Studio on October 5, 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
1st fastest of 2 runs of this model on Intel(R) Arc(TM) 140V GPU (16GB) · median 13.5 tok/s.
sort
- 113.8tok/s71.8Unsloth Studio · UD-Q4_K_XL · KV q8_0this run
- 213.3tok/s67.4llama.cpp
Reproduce this run
toolUnsloth Studio
modelunsloth/Qwen3.5-9B-GGUF (UD-Q4_K_XL)
context65,536
kv cacheq8_0
thinkingon
think limitnone
samplingtemperature 0.7 · top_p 0.8 · top_k 20 · min_p 0 · presence_penalty 1.5
clientv0.4.87+102
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "unsloth/Qwen3.5-9B-GGUF" --tool "Unsloth 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.