← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6

M5 Max (40c) · 128 GB · 6bit · 2026-04-28
Performance
16k
tokens
3,760
PP tok/s
88.8
TG tok/s
4358
TTFT (ms)
29.9
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8rc1
macOS macOS 26.5
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,558 309.9 29.4 GB view
4k 1,268 98.1 28.9 GB view
8k 3,891 95.4 29.2 GB view
16k 3,760 88.8 29.9 GB current
32k 3,225 75.5 31.2 GB view