← Back to community benchmarks

Qwen3-30B-A3B

M5 (10c) · 32 GB · 4bit · 2026-03-14
Performance
1k
tokens
864.3
PP tok/s
52.6
TG tok/s
1185
TTFT (ms)
16.6
Peak mem (GB)
Hardware
Chip M5 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.11
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 864.3 52.6 16.6 GB current
4k 993.4 43.8 17.0 GB view
8k 877.7 36.6 17.4 GB view
16k 639.6 26.3 18.1 GB view
32k 398.4 16.7 19.6 GB view
64k 221.9 10.0 22.7 GB view
Batching Results
Batch Size TG tok/s Speedup
52.6 1.00×
70.5 1.34×
82.3 1.56×