Benchmark result

Unsloth-Ornith-1.5-35B-A3B-UD-IQ3_XXS on 2× NVIDIA GeForce RTX 5060 — 87.2 tok/s

Measured with llama.cpp b10948-5f436dddb on September 13, 2026.

What the model built

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

7th fastest of 7 runs of this model on 2× NVIDIA GeForce RTX 5060 · Multi-GPU · median 88.5 tok/s.

sort

Compare the nearest 5 →

Reproduce this run

toolllama.cpp b10948-5f436dddb

modelUnsloth-Ornith-1.5-35B-A3B-UD-IQ3_XXS

context262,144

thinkingon

samplingtemperature 0.20000000298023224 · top_p 0.8999999761581421 · top_k 0 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1

clientv0.4.59+97

Set those in llama.cpp, then:

llm-benchmark benchmark --model "Unsloth-Ornith-1.5-35B-A3B-UD-IQ3_XXS" --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.