Benchmark result
JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M on NVIDIA GeForce RTX 2060 — 14.7 tok/s
Measured with llama.cpp manual on October 9, 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 2 runs of this model on NVIDIA GeForce RTX 2060 · median 15.6 tok/s.
sort
- 116.4tok/s62.3llama.cpp · Q4_K_M
- 214.7tok/s64.4llama.cpp · Q4_K_Mthis run
Reproduce this run
toolllama.cpp manual
modelJetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF:Q4_K_M (Q4_K_M)
context65,536
think limitnone
clientv0.4.89+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "JetBrains/Mellum2.1-12B-A2.5B-Thinking-GGUF: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.