Benchmark result
Swift-1.5-Qwen3.8-27B-IQ4_XS on NVIDIA TITAN RTX — 39.9 tok/s
Measured with llama.cpp on September 25, 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.
Reproduce this run
toolllama.cpp
modelSwift-1.5-Qwen3.8-27B-IQ4_XS
context128,000
effortxhigh (model default)
samplingtemperature 0.800000011920929 · top_p 0.949999988079071 · top_k 40 · min_p 0.05000000074505806 · presence_penalty 0 · repeat_penalty 1
clientv0.4.80+98
Set those in llama.cpp, then:
llm-benchmark benchmark --model "Swift-1.5-Qwen3.8-27B-IQ4_XS" --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.