← Back to community benchmarks

Qwen3.6-35B-A3B-OptiQ

M4 Max (40c) · 64 GB · 4bit · 2026-05-05
Performance
4k
tokens
840.6
PP tok/s
52.2
TG tok/s
4873
TTFT (ms)
21.6
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 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 698.7 54.7 20.8 GB view
4k 840.6 52.2 21.6 GB current
8k 837.2 47.3 22.0 GB view
16k 774.2 44.2 22.7 GB view