Benchmark result

Qwen3.8-27B-UD-IQ3_S on NVIDIA GeForce RTX 4090 — 58.2 tok/s

Measured with llama.cpp manual on November 2, 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

3rd fastest of 3 runs of this model on NVIDIA GeForce RTX 4090 · median 94.2 tok/s.

sort

199.8tok/s88.6llama.cpp
294.2tok/s87.7llama.cpp
358.2tok/s88.3llama.cppthis run

Compare the nearest 5 →

Qwen3.8-27B-UD-IQ3_S on other hardware

Reproduce this run

toolllama.cpp manual

modelQwen3.8-27B-UD-IQ3_S

context131,072

thinkingon

effortxhigh (model default)

think limitnone

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

clientv0.4.98+102

Set those in llama.cpp, then:

llm-benchmark benchmark --model "Qwen3.8-27B-UD-IQ3_S" --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.