Benchmark result
swift-qwen3.8-27b@iq2_xxs on AMD Radeon RX 9070/9070 XT/9070 GRE — 33.1 tok/s
Measured with LM Studio on September 15, 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.
Reproduce this run
toolLM Studio
modelswift-qwen3.8-27b@iq2_xxs
context136,192
clientv0.4.59+97
Set those in LM Studio, then:
llm-benchmark benchmark --model "swift-qwen3.8-27b@iq2_xxs" --tool "LM Studio"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.