← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 64 GB · 8bit · 2026-05-12
Performance
8k
tokens
3,898
PP tok/s
96.1
TG tok/s
2102
TTFT (ms)
36.7
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 26.4.1
Context 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,198 100.8 35.4 GB view
4k 3,653 97.8 36.2 GB view
8k 3,898 96.1 36.7 GB current
16k 3,765 91.5 37.4 GB view
32k 3,234 84.2 38.9 GB view
Batching Results
Batch Size TG tok/s Speedup
100.8 1.00×
247.4 2.45×