← Back to community benchmarks

Qwen3.6-35B-A3B

M3 Max (30c) · 36 GB · 4bit · 2026-04-28
Performance
32k
tokens
798.1
PP tok/s
44.8
TG tok/s
41058
TTFT (ms)
21.3
Peak mem (GB)
Hardware
Chip M3 Max (30c)
Memory 36 GB
GPU Cores 30
Software
oMLX v0.3.7
macOS macOS 15.7.5
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 866.8 83.3 18.3 GB view
4k 1,060 79.6 19.0 GB view
8k 1,066 73.7 19.4 GB view
16k 1,009 61.8 20.0 GB view
32k 798.1 44.8 21.3 GB current
Batching Results
Batch Size TG tok/s Speedup
83.3 1.00×
141.3 1.70×