← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · bf16 · 2026-04-17
Performance
4k
tokens
2,772
PP tok/s
70.8
TG tok/s
1478
TTFT (ms)
66.4
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 128 GB
GPU Cores 40
Software
oMLX v0.3.6
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,632 72.3 65.6 GB view
4k 2,772 70.8 66.4 GB current
Batching Results
Batch Size TG tok/s Speedup
72.3 1.00×
80.3 1.11×
129.3 1.79×