← Back to community benchmarks

Qwen3.5-4B

M4 (10c) · 24 GB · 4bit · 2026-03-09

Performance

1k

tokens

378.3

PP tok/s

35.1

TG tok/s

2707

TTFT (ms)

3.9

Peak mem (GB)

Hardware

Chip M4 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 15.7.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	378.3	35.1	3.9 GB	current
4k	380.6	34.1	4.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	35.1	1.00×
2×	67.6	1.93×
4×	86.9	2.48×