Benchmark result
Nex-N2.5-mini-IQ3_XXS on AMD Radeon RX 7800 XT — 92.3 tok/s
Measured with llama.cpp b10805-86b351fd6 on October 5, 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
4th fastest of 4 runs of this model on AMD Radeon RX 7800 XT · median 107.5 tok/s.
sort
- 1117.6tok/s82.9llama.cpp
- 2116.1tok/s84.3llama.cpp
- 398.9tok/s84.1llama.cpp
- 492.3tok/s80.6llama.cppthis run
Nex-N2.5-mini-IQ3_XXS on other hardware
Reproduce this run
toolllama.cpp b10805-86b351fd6
modelNex-N2.5-mini-IQ3_XXS
context131,072
think limitnone
samplingtemperature 0.6000000238418579 · top_p 0.949999988079071 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1.0499999523162842
clientv0.4.87+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Nex-N2.5-mini-IQ3_XXS" --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.