← Back to community benchmarks

Llama-3.2-1B-Instruct

M1 Max (24c) · 32 GB · 4bit · 2026-03-16

Performance

1k

tokens

1,771

PP tok/s

217.1

TG tok/s

579

TTFT (ms)

1.4

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.2.10

macOS macOS 26.3.1

Context 1,024

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,771	217.1	1.4 GB	current
4k	2,052	152.2	1.5 GB	view

Batching Results

Batch Size	TG tok/s	Speedup
1×	217.1	1.00×
2×	268.4	1.24×
4×	302.9	1.40×