← Back to community benchmarks

Llama-3.2-1B-Instruct

M2 (10c) · 24 GB · 4bit · 2026-03-10

Performance

4k

tokens

358.2

PP tok/s

27.5

TG tok/s

11438

TTFT (ms)

1.4

Peak mem (GB)

Hardware

Chip M2 (10c)

Memory 24 GB

GPU Cores 10

Software

oMLX v0.2.6

macOS macOS 26.3

Context 4,096

Performance by Context Length

Context	PP tok/s	TG tok/s	Peak Mem
1k	965.2	87.2	1.3 GB	view
4k	358.2	27.5	1.4 GB	current

Batching Results

Batch Size	TG tok/s	Speedup
1×	87.2	1.00×
2×	44.3	0.51×
4×	41.9	0.48×