← Back to community benchmarks

Qwen3.5-4B

M1 Max (32c) · 32 GB · 4bit · 2026-04-05

Performance

1k

tokens

270.4

PP tok/s

47.1

TG tok/s

3787

TTFT (ms)

4.0

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.3.0

macOS macOS 15.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	270.4	47.1	4.0 GB	current
4k	274.5	44.8	4.8 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	47.1	1.00×
2×	53.2	1.13×
4×	59.4	1.26×