Benchmark result
liquidai/lfm2.5-2.6b on NVIDIA GeForce RTX 4070 Ti SUPER — 99.4 tok/s
Measured with LM Studio on August 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.
How this run compares
2nd fastest of 2 runs of this model on NVIDIA GeForce RTX 4070 Ti SUPER · median 132.7 tok/s.
sort
- 1165.9tok/s60.1LM Studio
- 299.4tok/s53.6LM Studiothis run
Reproduce this run
toolLM Studio
modelliquidai/lfm2.5-2.6b
context32,768
clientv0.4.36+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "liquidai/lfm2.5-2.6b" --tool "LM 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.