← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M3 Max (30c) · 96 GB · 4bit · 2026-04-17
Performance
4k
tokens
1,120
PP tok/s
66.7
TG tok/s
3657
TTFT (ms)
21.0
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 96 GB
GPU Cores 30
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 939.7 69.2 20.2 GB view
4k 1,120 66.7 21.0 GB current