← Back to community benchmarks

Qwen3.5-4B

M1 Max (32c) · 64 GB · 4bit · 2026-03-11

Performance

1k

tokens

563.9

PP tok/s

86.6

TG tok/s

1816

TTFT (ms)

4.0

Peak mem (GB)

Hardware

Chip M1 Max (32c)

Memory 64 GB

GPU Cores 32

Software

oMLX v0.2.7

macOS macOS 26.4

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	563.9	86.6	4.0 GB	current
4k	444.1	69.1	4.2 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	86.6	1.00×
2×	87.4	1.01×
4×	88.7	1.02×