Benchmark result
unsloth/LFM2.5-230M-GGUF on Intel(R) Arc(TM) 140V GPU (16GB) — 272.5 tok/s
Measured with Unsloth Studio on September 21, 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
3rd fastest of 5 runs of this model on Intel(R) Arc(TM) 140V GPU (16GB) · median 272.5 tok/s.
sort
- 1359.5tok/s13.8llama.cpp
- 2290.6tok/s11.1llama.cpp
- 3272.5tok/s12.1Unsloth Studiothis run
- 4261.1tok/s13.6Unsloth Studio
- 5260.4tok/s16.7llama.cpp
Reproduce this run
toolUnsloth Studio
modelunsloth/LFM2.5-230M-GGUF
context128,000
thinkingoff
clientv0.4.71+98
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "unsloth/LFM2.5-230M-GGUF" --tool "Unsloth Studio"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.