← Back to community benchmarks

Llama-3.2-1B-Instruct

M4 Pro (20c) · 24 GB · 4bit · 2026-03-10

Performance

1k

tokens

2,297

PP tok/s

235.9

TG tok/s

446

TTFT (ms)

1.4

Peak mem (GB)

Hardware

Chip M4 Pro (20c)

Memory 24 GB

GPU Cores 20

Software

oMLX v0.2.7

macOS macOS 15.7.4

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	235.9	1.00×
2×	397.1	1.68×
4×	462.4	1.96×