← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6

M4 Max (40c) · 64 GB · 6bit · 2026-04-19
Performance
4k
tokens
506.7
PP tok/s
84.3
TG tok/s
8084
TTFT (ms)
28.5
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 4,096
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 current
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 view
64k 940.0 33.0 33.5 GB view
128k 505.0 19.2 38.9 GB view