← Back to community benchmarks

Qwen3.6-35B-A3B-q4

M4 Max (40c) · 64 GB · 4bit · 2026-04-16
Performance
8k
tokens
1,600
PP tok/s
94.1
TG tok/s
5119
TTFT (ms)
21.1
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,441 213.9 20.6 GB view
4k 691.7 99.5 20.8 GB view
8k 1,600 94.1 21.1 GB current
16k 3,244 46.0 22.3 GB view
32k 3,186 44.8 22.9 GB view
64k 2,432 43.9 24.8 GB view
128k 1,764 39.3 27.4 GB view