Benchmark result
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp on AMD Radeon RX 7800 XT — 39.6 tok/s
Measured with llama.cpp k5 v5 16384 budget manual on October 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
2nd fastest of 5 runs of this model on AMD Radeon RX 7800 XT · median 37.7 tok/s.
sort
- 148.9tok/s79.7llama.cpp
- 239.6tok/s87.4llama.cpp k5 v5 16384 budgetthis run
- 337.7tok/s88.1llama.cpp
- 437.2tok/s79.0llama.cpp
- 534.6tok/s83.1llama.cpp
Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp on other hardware
Reproduce this run
toolllama.cpp k5 v5 16384 budget manual
modelSwift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp
context65,536
thinkingon
clientv0.4.92+102
Set those in llama.cpp k5 v5 16384 budget, then:
llm-benchmark benchmark --model "Swift-1.5-Qwen3.8-27B-GSQ-RCO-IQ3_S-mtp" --tool "llama.cpp k5 v5 16384 budget"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.