← Back to community benchmarks

Qwen3.6-35B-A3B-UD

M3 Max (40c) · 128 GB · 4bit · 2026-05-02
Performance
1k
tokens
1,099
PP tok/s
80.6
TG tok/s
932
TTFT (ms)
20.4
Peak mem (GB)
Hardware
Chip M3 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.8
macOS macOS 15.7.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,099 80.6 20.4 GB current
4k 1,446 79.1 21.2 GB view
Batching Results
Batch Size TG tok/s Speedup
80.6 1.00×
131.5 1.63×
191.3 2.37×