← Back to community benchmarks

Qwen3.6-35B-A3B-oQ6

M2 Max (38c) · 64 GB · 6bit · 2026-04-26
Performance
4k
tokens
726.9
PP tok/s
62.5
TG tok/s
5635
TTFT (ms)
28.5
Peak mem (GB)
Hardware
Chip M2 Max (38c)
Memory 64 GB
GPU Cores 38
Software
oMLX v0.3.6
macOS macOS 15.7.4
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 600.6 66.4 27.7 GB view
4k 726.9 62.5 28.5 GB current
8k 732.4 59.4 28.9 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 66.4 1.00×
2× 100.5 1.51×
4× 131.7 1.98×