← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Max (40c) · 64 GB · 4bit · 2026-04-30
Performance
32k
tokens
1,316
PP tok/s
63.8
TG tok/s
24905
TTFT (ms)
23.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 1,572 77.1 22.2 GB view
32k 1,316 63.8 23.5 GB current