Benchmark result
Nex-N2.5-mini.APEX-I-MiniPlus-V2.1 on 2× NVIDIA GeForce RTX 5060 — 74.0 tok/s
Measured with llama.cpp b11217-c9064dded on September 27, 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
Nex-N2.5-mini.APEX-I-MiniPlus-V2.1 on other hardware
Reproduce this run
toolllama.cpp b11217-c9064dded
modelNex-N2.5-mini.APEX-I-MiniPlus-V2.1
context131,072
thinkingon
samplingtemperature 0.5 · top_p 0.949999988079071 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1
clientv0.4.82+98
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Nex-N2.5-mini.APEX-I-MiniPlus-V2.1" --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.