← Back to community benchmarks

Qwen3.6-35B-A3B

M1 Max (32c) · 64 GB · 6bit · 2026-04-26
Performance
4k
tokens
285.7
PP tok/s
50.0
TG tok/s
14337
TTFT (ms)
28.5
Peak mem (GB)
Hardware
Chip M1 Max (32c)
Memory 64 GB
GPU Cores 32
Software
oMLX v0.3.7
macOS macOS 26.4.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 447.9 132.0 28.7 GB view
4k 285.7 50.0 28.5 GB current
8k 570.8 46.9 28.9 GB view
16k 1,461 26.5 30.0 GB view
32k 1,406 26.1 30.6 GB view
64k 1,169 25.2 32.5 GB view
128k 752.7 24.1 35.2 GB view