← Back to community benchmarks

Qwen3.6-35B-A3B-Heretic

M4 Max (40c) · 48 GB · 4bit · 2026-04-25
Performance
1k
tokens
1,250
PP tok/s
325.6
TG tok/s
819
TTFT (ms)
20.6
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 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,250 325.6 20.6 GB current
4k 535.7 287.8 21.7 GB view
16k 685.6 196.4 22.5 GB view