← Back to community benchmarks

Qwen3-30B-A3B-Instruct-2507

M1 Ultra (48c) · 128 GB · 8bit · 2026-04-06
Performance
1k
tokens
589.7
PP tok/s
44.5
TG tok/s
1737
TTFT (ms)
30.8
Peak mem (GB)
Hardware
Chip M1 Ultra (48c)
Memory 128 GB
GPU Cores 48
Software
oMLX v0.3.4
macOS macOS 26.4
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 589.7 44.5 30.8 GB current
4k 654.3 41.5 31.3 GB view