← Back to community benchmarks

Qwen3-VL-8B-Instruct

M3 Pro (14c) · 18 GB · 4bit · 2026-03-10

Performance

4k

tokens

261.1

PP tok/s

23.6

TG tok/s

15685

TTFT (ms)

6.6

Peak mem (GB)

Hardware

Chip M3 Pro (14c)

Memory 18 GB

GPU Cores 14

Software

oMLX v0.2.7

macOS macOS 15.3.2

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	276.4	27.3	6.2 GB	view
4k	261.1	23.6	6.6 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	27.3	1.00×
2×	51.3	1.88×
4×	60.6	2.22×