Benchmark result
Cyber-Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1 on Intel Graphics — 21.9 tok/s
Measured with llama.cpp manual on October 3, 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
1st fastest of 5 runs of this model on Intel Graphics · median 21.2 tok/s.
sort
- 121.9tok/s84.3llama.cppthis run
- 221.3tok/s74.6llama.cpp
- 321.2tok/s83.3llama.cpp
- 420.3tok/s82.6llama.cpp:vulkan
- 514.0tok/s83.2llama.cpp
Cyber-Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1 on other hardware
Reproduce this run
toolllama.cpp manual
modelCyber-Tiel-Coder-35B-A3B.APEX-I-MiniPlus-V2.1
context200,000
thinkingon
effortminimal
think limitnone
samplingtemperature 0.8999999761581421 · top_p 0.949999988079071 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1
clientv0.4.87+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Cyber-Tiel-Coder-35B-A3B.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.