Benchmark result
unsloth/Qwen3.8-27B-GGUF:IQ3_S on NVIDIA GeForce RTX 4090 — 105.6 tok/s
Measured with llama.cpp b10660-6c84c7d5d on August 28, 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
4th fastest of 5 runs of this model on NVIDIA GeForce RTX 4090 · median 107.2 tok/s.
sort
- 1110.7tok/s86.5llama.cpp
- 2110.7tok/s86.5llama.cpp
- 3107.2tok/s86.4llama.cpp
- 4105.6tok/s88.4llama.cppthis run
- 587.3tok/s86.2llama.cpp
Reproduce this run
toolllama.cpp b10660-6c84c7d5d
modelunsloth/Qwen3.8-27B-GGUF:IQ3_S
context131,072
clientv0.4.44+97
Set those in llama.cpp, then:
llm-benchmark benchmark --model "unsloth/Qwen3.8-27B-GGUF: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.