← Back to community benchmarks

Qwen2-VL-2B-Instruct

M4 Pro (20c) · 24 GB · 8bit · 2026-03-12
Performance
1k
tokens
1,842
PP tok/s
119.0
TG tok/s
556
TTFT (ms)
2.2
Peak mem (GB)
Hardware
Chip M4 Pro (20c)
Memory 24 GB
GPU Cores 20
Software
oMLX v0.2.8
macOS macOS 26.3.1
Context 1,024
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 1,842 119.0 2.2 GB current
4k 2,002 108.7 2.3 GB view
8k 1,884 97.6 2.5 GB view
16k 1,587 83.7 2.5 GB view
32k 1,185 67.7 3.0 GB view
64k 740.0 48.2 3.9 GB view
Batching Results
Batch Size TG tok/s Speedup
119.0 1.00×
158.7 1.33×
203.6 1.71×
242.1 2.03×