Benchmark result
qwen3.8:27b-q4_K_M on 2× AMD Radeon RX 7800 XT — 25.9 tok/s
Measured with Ollama 0.40.2 on October 11, 2026.
Support llm-bench.io
llm-bench.io is free. If it helped you, I'd appreciate your support to cover the infrastructure costs.
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
4th fastest of 6 runs of this model on 2× AMD Radeon RX 7800 XT · Multi-GPU · median 26.4 tok/s.
sort
- 127.1tok/s79.6Ollama · Q4_K_M
- 227.0tok/s84.3Ollama · Q4_K_M
- 326.8tok/s83.8Ollama · Q4_K_M
- 425.9tok/s82.0Ollama · Q4_K_Mthis run
- 525.9tok/s89.3Ollama · Q4_K_M
- 625.9tok/s84.6Ollama · Q4_K_M
qwen3.8:27b-q4_K_M on other hardware
Reproduce this run
toolOllama 0.40.2
modelqwen3.8:27b-q4_K_M (Q4_K_M)
context65,536
thinkingon
effortmedium
samplingtemperature 1 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 0 · repeat_penalty 1
clientv0.4.89+102
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen3.8:27b-q4_K_M" --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.