Benchmark result
IsValorum/Ornith-1_5-35B-A3B_APEX-I-MiniPlus-V2_1 on NVIDIA GeForce RTX 3050 — 22.7 tok/s
Measured with llama.cpp manual on November 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; the frame only adds a line that tells this page how tall it is.
How this run compares
2nd fastest of 2 runs of this model on NVIDIA GeForce RTX 3050 · median 22.9 tok/s.
sort
- 123.1tok/s84.4llama.cpp
- 222.7tok/s79.0llama.cppthis run
Reproduce this run
toolllama.cpp manual
modelIsValorum/Ornith-1_5-35B-A3B_APEX-I-MiniPlus-V2_1
context65,536
thinkingoff
clientv0.4.98+102
Set those in llama.cpp, then:
llm-benchmark benchmark --model "IsValorum/Ornith-1_5-35B-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.