← Back to community benchmarks

Qwen3.5-2B

M1 (7c) · 8 GB · 6bit · 2026-03-19

Performance

4k

tokens

316.8

PP tok/s

31.6

TG tok/s

12928

TTFT (ms)

3.3

Peak mem (GB)

Hardware

Chip M1 (7c)

Memory 8 GB

GPU Cores 7

Software

oMLX v0.2.19

macOS macOS 15.7.4

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	318.3	33.0	2.9 GB	view
4k	316.8	31.6	3.3 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	33.0	1.00×
2×	45.4	1.38×
4×	46.9	1.42×