Benchmark result
GRM-3.2-Sky-ONYX-quality on Intel Graphics — 12.3 tok/s
Measured with ik_llama.cpp:cpu manual on October 10, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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
2nd fastest of 15 runs of this model on Intel Graphics · median 12.2 tok/s.
sort
- 112.3tok/s80.0ik_llama.cpp:cpu
- 212.3tok/s82.5ik_llama.cpp:cputhis run
- 312.3tok/s82.7ik_llama.cpp:cpu
- 412.3tok/s78.2ik_llama.cpp:cpu
- 512.2tok/s81.9ik_llama.cpp:cpu
- 612.2tok/s80.2ik_llama.cpp:cpu
- 712.2tok/s82.0ik_llama.cpp:cpu
- 812.2tok/s79.3ik_llama.cpp:cpu
- 912.1tok/s78.6ik_llama.cpp:cpu
- 1012.1tok/s56.4llama.cpp
- 1112.0tok/s79.0ik_llama.cpp:cpu
- 128.8tok/s80.7ik_llama.cpp:cpu
- 138.7tok/s79.5ik_llama.cpp:cpu
- 148.7tok/s74.3ik_llama.cpp:cpu
- 158.6tok/s74.8ik_llama.cpp:cpu
Reproduce this run
toolik_llama.cpp:cpu manual
modelGRM-3.2-Sky-ONYX-quality
context262,144
thinkingon
clientv0.4.87+102
Set those in ik_llama.cpp:cpu, then:
llm-benchmark benchmark --model "GRM-3.2-Sky-ONYX-quality" --tool "ik_llama.cpp:cpu"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.