← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Pro (16c) · 64 GB · 4bit · 2026-05-05
Performance
16k
tokens
679.8
PP tok/s
53.0
TG tok/s
24100
TTFT (ms)
21.9
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 64 GB
GPU Cores 16
Software
oMLX v0.3.6
macOS macOS 26.3
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 661.6 66.1 20.2 GB view
4k 748.7 63.0 21.0 GB view
8k 732.1 59.4 21.3 GB view
16k 679.8 53.0 21.9 GB current
32k 573.1 44.5 23.3 GB view
64k 451.5 32.6 26.0 GB view
128k 297.5 19.6 31.4 GB view
Batching Results
Batch Size TG tok/s Speedup
66.1 1.00×
97.3 1.47×
117.0 1.77×