← Back to community benchmarks

Qwen3.6-35B-A3B-PARO-packed

M5 Max (40c) · 128 GB · 4bit · 2026-06-07
Performance
64k
tokens
1,983
PP tok/s
59.4
TG tok/s
33048
TTFT (ms)
26.2
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.4.2rc1
macOS macOS 26.6
Context 65,536
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,162 78.1 20.5 GB view
4k 3,410 70.5 21.3 GB view
8k 3,240 80.6 21.6 GB view
16k 3,195 73.1 22.3 GB view
32k 2,704 68.6 23.6 GB view
64k 1,983 59.4 26.2 GB current
Batching Results
Batch Size TG tok/s Speedup
78.1 1.00×
115.9 1.48×
232.6 2.98×