← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M3 Max (30c) · 36 GB · 4bit · 2026-05-14
Performance
1k
tokens
944.6
PP tok/s
67.2
TG tok/s
1084
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.9.dev2
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 944.6 67.2 20.4 GB current
4k 1,133 64.1 21.2 GB view
Batching Results
Batch Size TG tok/s Speedup
1× 67.2 1.00×
2× 109.0 1.62×
4× 156.8 2.33×