← Back to community benchmarks

Qwen3.6-35B-A3B-Hereticmixed-6.4bit

M4 Pro (16c) · 48 GB · 6bit · 2026-04-30
Performance
1k
tokens
640.9
PP tok/s
59.3
TG tok/s
1598
TTFT (ms)
26.6
Peak mem (GB)
Hardware
Chip M4 Pro (16c)
Memory 48 GB
GPU Cores 16
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 640.9 59.3 26.6 GB current
4k 727.4 56.2 27.4 GB view
8k 713.9 53.3 27.7 GB view
16k 663.4 47.1 28.3 GB view
32k 574.0 38.4 29.7 GB view
64k 446.3 28.0 32.4 GB view