← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · unknown · 2026-04-18
Performance
8k
tokens
3,627
PP tok/s
67.4
TG tok/s
2259
TTFT (ms)
66.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.5
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,865 71.1 65.6 GB view
4k 3,357 69.2 66.4 GB view
8k 3,627 67.4 66.7 GB current
16k 3,530 64.0 67.4 GB view
32k 3,112 56.9 68.7 GB view
64k 2,367 45.8 71.3 GB view
128k 1,519 33.4 76.8 GB view