Benchmark result
mradermacher-GRM-3.2-Sky.i1-Q6_K on Intel Graphics — 10.8 tok/s
Measured with ik_llama.cpp:cpu manual on October 9, 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
6th fastest of 6 runs of this model on Intel Graphics · median 10.9 tok/s.
sort
- 112.3tok/s78.4ik_llama.cpp:cpu · Q6_K
- 211.0tok/s79.7llama.cpp:cpu · Q6_K
- 310.9tok/s76.5llama.cpp:cpu · Q6_K
- 410.9tok/s76.1llama.cpp:cpu · Q6_K
- 510.8tok/s83.3llama.cpp:cpu · Q6_K
- 610.8tok/s80.2ik_llama.cpp:cpu · Q6_Kthis run
Reproduce this run
toolik_llama.cpp:cpu manual
modelmradermacher-GRM-3.2-Sky.i1-Q6_K (Q6_K)
context262,144
thinkingon
clientv0.4.87+102
Set those in ik_llama.cpp:cpu, then:
llm-benchmark benchmark --model "mradermacher-GRM-3.2-Sky.i1-Q6_K" --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.