← Back to community benchmarks

Qwen3.5-2B

M1 (7c) · 8 GB · 6bit · 2026-03-11

Performance

1k

tokens

319.8

PP tok/s

33.6

TG tok/s

3202

TTFT (ms)

2.9

Peak mem (GB)

Hardware

Chip M1 (7c)

Memory 8 GB

GPU Cores 7

Software

oMLX v0.2.7

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	319.8	33.6	2.9 GB	current
4k	320.1	32.6	3.0 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	33.6	1.00×
2×	47.9	1.43×
4×	49.4	1.47×