← Back to community benchmarks

Qwen3.5-2B

M1 (8c) · 16 GB · 6bit · 2026-03-10

Performance

1k

tokens

357.3

PP tok/s

32.6

TG tok/s

2866

TTFT (ms)

2.9

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.2.6

macOS macOS 26.2

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	357.3	32.6	2.9 GB	current
4k	362.1	28.9	3.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	32.6	1.00×
2×	52.4	1.61×
4×	54.8	1.68×