Benchmark result
LFM2.5-8B-A1B-Q4_K_M on NVIDIA GeForce RTX 4070 — 282.5 tok/s
Measured with llama.cpp unsloth-studio/v0.1.810-beta on September 18, 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 4 runs of this model on NVIDIA GeForce RTX 4070 · median 282.0 tok/s.
sort
- 1285.0tok/s49.0llama.cpp · Q4_K_M
- 2282.5tok/s46.6llama.cpp · Q4_K_Mthis run
- 3281.5tok/s55.0llama.cpp · Q4_K_M
- 4275.9tok/s50.9llama.cpp · Q4_K_M
Reproduce this run
toolllama.cpp unsloth-studio/v0.1.810-beta
modelLFM2.5-8B-A1B-Q4_K_M (Q4_K_M)
context16,384
thinkingon
samplingtemperature 0.800000011920929 · top_p 0.949999988079071 · top_k 40 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.59+97
Set those in llama.cpp, then:
llm-benchmark benchmark --model "LFM2.5-8B-A1B-Q4_K_M" --tool "llama.cpp"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.