← Back to community benchmarks

Qwen3.5-4B

M1 Max (32c) · 32 GB · 4bit · 2026-03-13

Performance

1k

tokens

547.2

PP tok/s

84.5

TG tok/s

1871

TTFT (ms)

4.0

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 32 GB

GPU Cores 32

Software

oMLX v0.2.6

macOS macOS 15.6

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	547.2	84.5	4.0 GB	current
4k	548.7	78.5	4.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	84.5	1.00×
2×	107.1	1.27×
4×	120.9	1.43×