Benchmark result
mradermacher-GRM-3.2-Sky.i1-Q5_K_M on Intel Graphics — 13.3 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
4th fastest of 4 runs of this model on Intel Graphics · median 13.5 tok/s.
sort
- 113.5tok/s79.2ik_llama.cpp:cpu · Q5_K_M
- 213.5tok/s75.1ik_llama.cpp:cpu · Q5_K_M
- 313.5tok/s83.6ik_llama.cpp:cpu · Q5_K_M
- 413.3tok/s79.5ik_llama.cpp:cpu · Q5_K_Mthis run
Reproduce this run
toolik_llama.cpp:cpu manual
modelmradermacher-GRM-3.2-Sky.i1-Q5_K_M (Q5_K_M)
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-Q5_K_M" --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.