← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-10

Performance

1k

tokens

144.0

PP tok/s

21.1

TG tok/s

7112

TTFT (ms)

3.9

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.7

macOS macOS 26.3

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	21.1	1.00×
2×	32.6	1.55×
4×	32.8	1.55×