← Back to community benchmarks

Qwen3-30B-A3B-Instruct-2507

M3 Ultra (60c) · 256 GB · 8bit · 2026-03-09
Performance
1k
tokens
1,410
PP tok/s
74.4
TG tok/s
727
TTFT (ms)
30.8
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 256 GB
GPU Cores 60
Software
oMLX v0.2.6
macOS macOS 15.6.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,410 74.4 30.8 GB current
4k 1,685 63.8 31.3 GB view
Batching Results
Batch Size TG tok/s Speedup
74.4 1.00×
125.4 1.69×
181.0 2.43×