← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Max (40c) · 64 GB · 4bit · 2026-05-11
Performance
1k
tokens
1,233
PP tok/s
95.5
TG tok/s
831
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,233 95.5 20.4 GB current
4k 1,643 88.2 21.2 GB view