Benchmark result
fauxpaslife/Mellum2-Thinking-A2.5B-12B:latest on NVIDIA GeForce RTX 4070 Ti — 172.3 tok/s
Measured with Ollama 0.40.6 on October 21, 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
toolOllama 0.40.6
modelfauxpaslife/Mellum2-Thinking-A2.5B-12B:latest (Q4_K_M)
context65,536
samplingtemperature 0.6 · top_p 0.95 · top_k 20
clientv0.4.96+102
Set those in Ollama, then:
llm-benchmark benchmark --model "fauxpaslife/Mellum2-Thinking-A2.5B-12B:latest" --tool "Ollama"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.