Benchmark result
hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S on AMD Radeon RX 7900 XTX — 18.6 tok/s
Measured with Ollama 0.34.1 on September 20, 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
3rd fastest of 3 runs of this model on AMD Radeon RX 7900 XTX · median 29.9 tok/s.
sort
- 134.4tok/s85.6Ollama · IQ3_S
- 229.9tok/s85.8Ollama · IQ3_S
- 318.6tok/s84.7Ollama · IQ3_Sthis run
hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S on other hardware
Reproduce this run
toolOllama 0.34.1
modelhf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S (IQ3_S)
context180,000
thinkingon
effortxhigh (model default)
clientv0.4.71+98
Set those in Ollama, then:
llm-benchmark benchmark --model "hf.co/ISTA-DASLab/Qwen3.8-27B-GSQ-RCO-GGUF:IQ3_S" --tool "Ollama"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.