← Back to community benchmarks

Qwen3-VL-30B-A3B-Instruct

M3 Ultra (60c) · 96 GB · 4bit · 2026-03-10
Performance
1k
tokens
1,698
PP tok/s
78.2
TG tok/s
603
TTFT (ms)
17.6
Peak mem (GB)
Hardware
Chip M3 Ultra (60c)
Memory 96 GB
GPU Cores 60
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,698 78.2 17.6 GB current
4k 1,881 68.7 18.1 GB view
Batching Results
Batch Size TG tok/s Speedup
78.2 1.00×
128.8 1.65×
51.5 0.66×