Benchmark result
Qwen/Qwen2.5-Coder-14B-Instruct-GGUF on Intel Arc B390 — 8.3 tok/s
Measured with llama.cpp b11459-f498f864f on October 10, 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
4th fastest of 4 runs of this model on Intel Arc B390 · median 8.4 tok/s.
sort
- 18.4tok/s54.6llama.cpp
- 28.4tok/s46.7llama.cpp
- 38.4tok/s56.4llama.cpp
- 48.3tok/s58.6llama.cppthis run
Reproduce this run
toolllama.cpp b11459-f498f864f
modelQwen/Qwen2.5-Coder-14B-Instruct-GGUF
context8,192
samplingtemperature 0.800000011920929 · top_p 0.949999988079071 · top_k 40 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.89+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Qwen/Qwen2.5-Coder-14B-Instruct-GGUF" --tool "llama.cpp"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.