← Back to community benchmarks

Llama-3.2-1B-Instruct

M4 Max (40c) · 128 GB · 4bit · 2026-03-10

Performance

1k

tokens

4,050

PP tok/s

402.1

TG tok/s

253

TTFT (ms)

1.4

Peak mem (GB)

Hardware

Chip M4 Max (40c)

Memory 128 GB

GPU Cores 40

Software

oMLX v0.2.7

macOS macOS 26.3

Context 1,024

Batching Results

Batch Size	TG tok/s	Speedup
1×	402.1	1.00×
2×	678.1	1.69×
4×	770.1	1.92×