← Back to community benchmarks

Qwen3-30B-A3B-Instruct-2507-4bit-ODWQ

M4 Pro (20c) · 48 GB · 4bit · 2026-03-14
Performance
4k
tokens
730.7
PP tok/s
64.9
TG tok/s
5605
TTFT (ms)
17.1
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 48 GB
GPU Cores 20
Software
oMLX v0.2.11
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 759.9 76.8 16.6 GB view
4k 730.7 64.9 17.1 GB current
8k 632.2 52.8 17.4 GB view
16k 485.3 40.5 18.2 GB view