Benchmark result
apodex_Apodex-1.1-mini-IQ2_M on 2× NVIDIA GeForce RTX 5060 — 103.0 tok/s
Measured with llama.cpp b11253-86ea01d05 on October 1, 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.
How this run compares
2nd fastest of 4 runs of this model on 2× NVIDIA GeForce RTX 5060 · Multi-GPU · median 94.6 tok/s.
sort
- 1103.1tok/s67.3llama.cpp
- 2103.0tok/s80.4llama.cppthis run
- 386.3tok/s62.6llama.cpp
- 485.0tok/s53.3llama.cpp
Reproduce this run
toolllama.cpp b11253-86ea01d05
modelapodex_Apodex-1.1-mini-IQ2_M
context131,072
thinkingon
samplingtemperature 0.6000000238418579 · top_p 0.949999988079071 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1.0499999523162842
clientv0.4.85+101
Set those in llama.cpp, then:
llm-benchmark benchmark --model "apodex_Apodex-1.1-mini-IQ2_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.