← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Max (40c) · 128 GB · 4bit · 2026-04-29
Performance
32k
tokens
1,206
PP tok/s
52.4
TG tok/s
27176
TTFT (ms)
23.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 15.6
Context 32,768