Benchmark result
ddalcu/Qwen3.8-Flash-Next-MLX-Serve-mixed-4-8bit on Apple M4 Max — 70.9 tok/s
Measured with vLLM on September 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
3rd fastest of 3 runs of this model on Apple M4 Max · median 71.6 tok/s.
sort
- 172.0tok/s67.9vLLM
- 271.6tok/s68.4vLLM
- 370.9tok/s75.6vLLMthis run
Reproduce this run
toolvLLM
modelddalcu/Qwen3.8-Flash-Next-MLX-Serve-mixed-4-8bit
context262,144
thinkingon
effortxhigh (model default)
clientv0.4.59+97
Set those in vLLM, then:
llm-benchmark benchmark --model "ddalcu/Qwen3.8-Flash-Next-MLX-Serve-mixed-4-8bit" --tool "vLLM"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.