Benchmark result
MiniCPM-V-4.7-35B-A3B.APEX-I-NanoPlus-V2.1 on 2× NVIDIA GeForce RTX 5060 — 95.0 tok/s
Measured with llama.cpp b11729-412a363c6 on October 19, 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 3 runs of this model on 2× NVIDIA GeForce RTX 5060 · Multi-GPU · median 95.0 tok/s.
sort
- 1100.4tok/s77.1llama.cpp
- 295.0tok/s76.3llama.cppthis run
- 382.7tok/s74.9llama.cpp
Reproduce this run
toolllama.cpp b11729-412a363c6
modelMiniCPM-V-4.7-35B-A3B.APEX-I-NanoPlus-V2.1
context131,072
thinkingon
think limitnone
samplingtemperature 0.6000000238418579 · top_p 0.8999999761581421 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1.0499999523162842
clientv0.4.96+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "MiniCPM-V-4.7-35B-A3B.APEX-I-NanoPlus-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.