← Back to community benchmarks

Qwen3.5-4B

M4 Max (40c) · 48 GB · 4bit · 2026-03-10

Performance

1k

tokens

1,575

PP tok/s

143.6

TG tok/s

650

TTFT (ms)

4.0

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 48 GB

GPU Cores 40

Software

oMLX v0.2.6

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,575	143.6	4.0 GB	current
4k	1,579	135.1	4.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	143.6	1.00×
2×	256.5	1.79×
4×	306.0	2.13×