← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M3 Pro (18c) · 36 GB · 4bit · 2026-05-15
Performance
4k
tokens
659.4
PP tok/s
36.2
TG tok/s
6212
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip M3 Pro (18c)
Memory 36 GB
GPU Cores 18
Software
oMLX v0.3.8
macOS macOS 15.7.5
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 574.4 37.0 20.4 GB view
4k 659.4 36.2 21.2 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 37.0 1.00×
2× 60.8 1.64×
4× 88.4 2.39×