Benchmark result
qwen3.6:35b-a3b-mtp-q4_K_M on AMD Radeon RX 7600 XT — 45.3 tok/s
Measured with Ollama 0.40.14 on November 5, 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
1st fastest of 2 runs of this model on AMD Radeon RX 7600 XT · median 44.1 tok/s.
sort
- 145.3tok/s64.4Ollama · Q4_K_Mthis run
- 243.0tok/s79.3Ollama · Q4_K_M
Reproduce this run
toolOllama 0.40.14
modelqwen3.6:35b-a3b-mtp-q4_K_M (Q4_K_M)
context8,192
samplingtemperature 1 · top_p 0.95 · top_k 20 · min_p 0 · presence_penalty 1.5 · repeat_penalty 1
clientv0.4.98+102
Set those in Ollama, then:
llm-benchmark benchmark --model "qwen3.6:35b-a3b-mtp-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.