← Back to community benchmarks

Llama-3.2-1B-Instruct

M1 Max (24c) · 32 GB · 4bit · 2026-03-12

Performance

4k

tokens

1,292

PP tok/s

116.8

TG tok/s

3172

TTFT (ms)

1.5

Peak mem (GB)

Hardware

Chip M1 Max (24c)

Memory 32 GB

GPU Cores 24

Software

oMLX v0.2.9

macOS macOS 26.3.1

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	1,109	173.1	1.4 GB	view
4k	1,292	116.8	1.5 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	173.1	1.00×
2×	202.5	1.17×
4×	220.3	1.27×