← Back to community benchmarks

Qwen3-VL-4B-Instruct

M1 (8c) · 16 GB · 4bit · 2026-03-11
Performance
4k
tokens
133.4
PP tok/s
18.1
TG tok/s
30699
TTFT (ms)
4.0
Peak mem (GB)
Hardware
Chip M1 (8c)
Memory 16 GB
GPU Cores 8
Software
oMLX v0.2.7
macOS macOS 26.3.1
Context 4,096
Performance by Context Length
Context PP tok/s TG tok/s Peak Mem
1k 144.5 20.7 3.6 GB view
4k 133.4 18.1 4.0 GB current
Batching Results
Batch Size TG tok/s Speedup
20.7 1.00×
31.3 1.51×
29.9 1.44×