Benchmark result
ukisai/Swift-1.5-Qwen3.8-27B-GGUF on 2× AMD Radeon RX 7900 XT/7900 XTX/7900M — 40.7 tok/s
Measured with Unsloth Studio on September 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.
How this run compares
3rd fastest of 3 runs of this model on 2× AMD Radeon RX 7900 XT/7900 XTX/7900M · Multi-GPU · median 60.7 tok/s.
sort
- 164.7tok/s77.5Unsloth Studio · Q6_K · KV f16
- 260.7tok/s88.8Unsloth Studio · Q6_K · KV f16
- 340.7tok/s68.1Unsloth Studio · Q4_K_M · KV f16this run
Reproduce this run
toolUnsloth Studio
modelukisai/Swift-1.5-Qwen3.8-27B-GGUF (Q4_K_M)
context8,192
kv cachef16 (assumed default)
effortxhigh (model default)
samplingtemperature 0.7 · top_p 0.8 · top_k 20 · min_p 0 · presence_penalty 1.5
clientv0.4.82+98
Set those in Unsloth Studio, then:
llm-benchmark benchmark --model "ukisai/Swift-1.5-Qwen3.8-27B-GGUF" --tool "Unsloth 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.