← Back to community benchmarks

Qwen3.6-35B-A3B

M5 Max (40c) · 128 GB · bf16 · 2026-04-18
Performance
8k
tokens
3,681
PP tok/s
68.7
TG tok/s
2226
TTFT (ms)
66.7
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 8,192
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 2,061 157.0 67.0 GB view
4k 506.6 70.9 66.4 GB view
8k 3,681 68.7 66.7 GB current
16k 3,593 63.3 67.4 GB view
32k 3,123 53.5 68.7 GB view
64k 2,270 38.9 71.3 GB view
128k 1,466 24.6 76.8 GB view
195k 1,065 17.9 82.5 GB view