← Back to community benchmarks

Qwen3.6-35B-A3B-Heretic

M4 Max (40c) · 48 GB · 4bit · 2026-04-25
Performance
16k
tokens
685.6
PP tok/s
196.4
TG tok/s
23899
TTFT (ms)
22.5
Peak mem (GB)
Hardware
Chip M4 Max (40c)
Memory 48 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 1,250 325.6 20.6 GB view
4k 535.7 287.8 21.7 GB view
16k 685.6 196.4 22.5 GB current