← Back to community benchmarks

Qwen3.6-35B-A3B-oQ4

M5 Max (40c) · 128 GB · 4bit · 2026-04-20
Performance
4k
tokens
1,331
PP tok/s
112.8
TG tok/s
3078
TTFT (ms)
20.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
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 2,734 436.7 21.3 GB view
4k 1,331 112.8 20.7 GB current
8k 3,885 104.7 21.1 GB view
16k 3,621 95.9 21.7 GB view
32k 2,642 73.9 23.0 GB view
64k 1,975 47.6 25.7 GB view