← Back to community benchmarks

Qwen3.5-9B

M1 (8c) · 16 GB · 4bit · 2026-04-15

Performance

1k

tokens

76.4

PP tok/s

12.9

TG tok/s

13400

TTFT (ms)

5.7

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

Software

oMLX v0.3.5.dev1

macOS macOS 26.4.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	76.4	12.9	5.7 GB	current
4k	78.1	12.5	6.3 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	12.9	1.00×
2×	18.7	1.45×
4×	19.2	1.49×