← Back to community benchmarks

Qwen3-VL-8B-Instruct-oQ8

M1 Ultra (48c) · 64 GB · 8bit · 2026-05-10

Performance

1k

tokens

750.0

PP tok/s

32.4

TG tok/s

1365

TTFT (ms)

9.9

Peak mem (GB)

Hardware

Chip M1 Ultra (48c)

Memory 64 GB

GPU Cores 48

Software

oMLX v0.3.8

macOS macOS 26.3

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	750.0	32.4	9.9 GB	current
4k	760.4	29.8	10.6 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	32.4	1.00×
2×	53.7	1.66×
4×	72.7	2.24×