← Back to community benchmarks

Qwen3.6-35B-A3B

M4 Max (40c) · 64 GB · 4bit · 2026-04-29
Performance
8k
tokens
1,735
PP tok/s
112.9
TG tok/s
4721
TTFT (ms)
20.4
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 1,397 121.7 19.3 GB view
4k 1,743 116.8 20.0 GB view
8k 1,735 112.9 20.4 GB current
Batching Results
Batch Size TG tok/s Speedup
121.7 1.00×
196.2 1.61×
483.4 3.97×
790.2 6.49×