← Back to community benchmarks

Qwen3.6-35B-A3B-OptiQ

M5 Pro (16c) · 48 GB · 4bit · 2026-07-21
Performance
4k
tokens
1,939
PP tok/s
70.7
TG tok/s
2113
TTFT (ms)
22.7
Peak mem (GB)
Hardware
Chip M5 Pro (16c)
Memory 48 GB
GPU Cores 16
Software
oMLX v0.5.2
macOS macOS 26.5.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,093 73.7 21.8 GB view
4k 1,939 70.7 22.7 GB current
Batching Results
Batch Size TG tok/s Speedup
73.7 1.00×
119.4 1.62×
176.7 2.40×