Benchmark result

Mellum2-12B-A2.5B-Instruct-MXFP4_MOE on NVIDIA GeForce RTX 4060 Laptop GPU — 84.5 tok/s

Measured with llama.cpp b11985-6d194531e on October 31, 2026.

What the model built

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

10th fastest of 10 runs of this model on NVIDIA GeForce RTX 4060 Laptop GPU · median 87.2 tok/s.

sort

Compare the nearest 5 →

Reproduce this run

toolllama.cpp b11985-6d194531e

modelMellum2-12B-A2.5B-Instruct-MXFP4_MOE

context32,768

think limitnone

samplingtemperature 0.800000011920929 · top_p 0.949999988079071 · top_k 40 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1

clientv0.4.98+102

Set those in llama.cpp, then:

llm-benchmark benchmark --model "Mellum2-12B-A2.5B-Instruct-MXFP4_MOE" --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.