Benchmark result
Qwen3.8-27B-UD-IQ3_XXS on 3× NVIDIA GeForce RTX 5070 Ti — 72.1 tok/s
Measured with llama.cpp b11029-5c53396b8 on September 18, 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 2 runs of this model on 3× NVIDIA GeForce RTX 5070 Ti · Multi-GPU · median 70.9 tok/s.
sort
- 172.1tok/s40.2llama.cppthis run
- 269.7tok/s56.3llama.cpp
Qwen3.8-27B-UD-IQ3_XXS on other hardware
Reproduce this run
toolllama.cpp b11029-5c53396b8
modelQwen3.8-27B-UD-IQ3_XXS
context8,192
effortxhigh (model default)
samplingtemperature 1 · 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-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.