← Back to community benchmarks

Llama-3.2-1B-Instruct

M1 (8c) · 16 GB · 4bit · 2026-03-12

Performance

4k

tokens

809.9

PP tok/s

49.4

TG tok/s

5059

TTFT (ms)

1.4

Peak mem (GB)

Hardware

Chip M1 (8c)

Memory 16 GB

GPU Cores 8

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	827.9	67.5	1.3 GB	view
4k	809.9	49.4	1.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	67.5	1.00×
2×	115.5	1.71×
4×	120.2	1.78×