← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M3 Max (40c) · 128 GB · 4bit · 2026-05-02
Performance
4k
tokens
742.9
PP tok/s
79.5
TG tok/s
5514
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,247 154.4 21.7 GB view
4k 742.9 79.5 21.2 GB current
8k 1,444 73.6 21.5 GB view