← Back to community benchmarks

Qwen3.5-4B

M3 Ultra (60c) · 96 GB · unknown · 2026-03-10

Performance

1k

tokens

1,247

PP tok/s

17.3

TG tok/s

821

TTFT (ms)

12.0

Peak mem (GB)

Hardware

Chip M3 Ultra (60c)

Memory 96 GB

GPU Cores 60

Software

oMLX v0.2.6

macOS macOS 15.3

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	17.3	1.00×
2×	21.6	1.25×
4×	42.4	2.45×