Benchmark result
LFM2.5-24B-A2B.APEX-I-MiniPlus-V2.1 on Intel Graphics — 28.4 tok/s
Measured with llama.cpp:vulkan manual on October 15, 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
2nd fastest of 3 runs of this model on Intel Graphics · median 28.4 tok/s.
sort
- 129.6tok/s70.4llama.cpp
- 228.4tok/s56.6llama.cpp:vulkanthis run
- 316.3tok/s68.2llama.cpp:sycl
Reproduce this run
toolllama.cpp:vulkan manual
modelLFM2.5-24B-A2B.APEX-I-MiniPlus-V2.1
context65,536
thinkingon
clientv0.4.87+102
Set those in llama.cpp:vulkan, then:
llm-benchmark benchmark --model "LFM2.5-24B-A2B.APEX-I-MiniPlus-V2.1" --tool "llama.cpp:vulkan"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.