Benchmark result

Qwen3.8-27B-UD-Q3_K_XL on 2× NVIDIA GeForce RTX 5070 Ti — 46.9 tok/s

Measured with llama.cpp b11029-5c53396b8 on September 18, 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

Qwen3.8-27B-UD-Q3_K_XL on other hardware

Reproduce this run

toolllama.cpp b11029-5c53396b8

modelQwen3.8-27B-UD-Q3_K_XL (Q3_K)

context32,768

effortxhigh (model default)

samplingtemperature 0 · top_p 0.949999988079071 · top_k 20 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1

clientv0.4.59+97

Set those in llama.cpp, then:

llm-benchmark benchmark --model "Qwen3.8-27B-UD-Q3_K_XL" --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.