← Back to community benchmarks

Qwen3-VL-30B-A3B-Instruct

M4 (10c) · 32 GB · 4bit · 2026-03-09
Performance
1k
tokens
424.1
PP tok/s
41.1
TG tok/s
2415
TTFT (ms)
17.5
Peak mem (GB)
Hardware
Chip M4 (10c)
Memory 32 GB
GPU Cores 10
Software
oMLX v0.2.6
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 424.1 41.1 17.5 GB current
4k 376.9 34.0 18.1 GB view
Batching Results
Batch Size TG tok/s Speedup
41.1 1.00×
54.7 1.33×
58.5 1.42×