← Back to community benchmarks

Qwen3.6-35B-A3B-Claude-4.7-Opus-Reasoning-DistilledoQ4-MTP

M5 Pro (20c) · 64 GB · 4bit · 2026-07-01
Performance
32k
tokens
1,759
PP tok/s
77.2
TG tok/s
18633
TTFT (ms)
22.7
Peak mem (GB)
Hardware
Chip M5 Pro (20c)
Memory 64 GB
GPU Cores 20
Software
oMLX v0.4.4
macOS macOS 26.5.1
Context 32,768
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
16k 2,085 90.3 21.0 GB view
32k 1,759 77.2 22.7 GB current
64k 1,308 64.4 25.7 GB view