← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6

M4 Max (40c) · 64 GB · 6bit · 2026-04-19
Performance
32k
tokens
1,167
PP tok/s
50.0
TG tok/s
28085
TTFT (ms)
30.8
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.3.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,332 287.5 29.1 GB view
4k 506.7 84.3 28.5 GB view
8k 1,626 79.7 28.9 GB view
16k 1,477 72.1 29.5 GB view
32k 1,167 50.0 30.8 GB current
64k 940.0 33.0 33.5 GB view
128k 505.0 19.2 38.9 GB view