← Back to community benchmarks

Qwen3.6-35B-A3B-5bit

M5 Max (40c) · 64 GB · 5bit · 2026-04-24
Performance
16k
tokens
3,715
PP tok/s
99.4
TG tok/s
4411
TTFT (ms)
25.1
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8.dev1
macOS macOS 26.4.1
Context 16,384
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,621 115.4 23.3 GB view
16k 3,715 99.4 25.1 GB current
32k 3,211 80.1 26.4 GB view