← Back to community benchmarks

Qwen3.5-4B

M1 (8c) · 16 GB · 4bit · 2026-03-09

Performance

1k

tokens

145.4

PP tok/s

23.0

TG tok/s

7042

TTFT (ms)

3.9

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

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	145.4	23.0	3.9 GB	current
4k	145.1	21.7	4.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	23.0	1.00×
2×	33.4	1.45×
4×	34.5	1.50×