Benchmark result
saidutta69/lfm2.5-2.6b-fable5-coding-agent-heretic on AMD Radeon RX 7900 GRE — 82.9 tok/s
Measured with Unsloth Studio on October 12, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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.
Reproduce this run
toolUnsloth Studio
modelsaidutta69/lfm2.5-2.6b-fable5-coding-agent-heretic (F16)
context65,536
kv cachef16
thinkingon
think limitnone
samplingtemperature 0.1 · top_p 0.1 · top_k 50 · min_p 0.15 · presence_penalty 0
clientv0.4.92+102
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "saidutta69/lfm2.5-2.6b-fable5-coding-agent-heretic" --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.