← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M4 Max (40c) · 48 GB · 4bit · 2026-05-18
Performance
4k
tokens
1,599
PP tok/s
80.5
TG tok/s
2562
TTFT (ms)
21.2
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 GB
GPU Cores 40
Software
oMLX v0.3.9.dev1
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 966.7 89.4 20.4 GB view
4k 1,599 80.5 21.2 GB current
Batching Results
Batch Size TG tok/s Speedup
1× 89.4 1.00×
2× 132.5 1.48×
4× 198.3 2.22×