← Back to community benchmarks

Qwen3.6-35B-A3B-Hereticmixed-3.9bit

M5 Max (40c) · 64 GB · 4bit · 2026-04-30
Performance
1k
tokens
1,815
PP tok/s
134.4
TG tok/s
564
TTFT (ms)
17.6
Peak mem (GB)
Hardware
Chip M5 Max (40c)
Memory 64 GB
GPU Cores 40
Software
oMLX v0.3.8rc1
macOS macOS 26.4.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,815 134.4 17.6 GB current
8k 3,903 112.4 18.8 GB view
16k 3,870 106.5 19.4 GB view