models · meta-llama

Llama-3.2-1B-Instruct

Smallest Llama 3.2 model. On-device, edge-optimized, multilingual.

What this registry has checked

Quarantine. We hold the publisher’s own published hash for these weights and have recorded it against this entry. We have not downloaded and hashed the weights ourselves, so the hash is the publisher’s claim, not our measurement.

Weight file SHA-256	fc19e633aae49536a20f227c1577dd27b77cc39dde1496bd2c498a76d13766e3
Method	self-download-failed

Re-check this yourself → Source → Full record →

What is recorded

Publisher	meta-llama
Origin	United States
Licence	Llama-3.2-Community
Publisher’s own licence statement	llama3.2
Parameters	1,235,814,400 (1.24B)
Context window	60,000 tokens
Modality	text->text
Native precision	BF16
Pulls recorded here	54,014
Downloads reported upstream	6,303,233

Measured on real hardware

None of these runs are ours. Each figure is the reporter’s, linked to their own evidence, under their own trust label. The number shown is single-stream decode — one user, concurrency 1 — because aggregate throughput across many users is a different quantity and reads as far faster than anyone will see.

Reported to local-ai-registry

Hardware	Engine	Build measured	Decode, 1 stream	Label	Reported by
GeForce RTX 5080	llama.cpp	Q8_0	448 tok/s @ 4,096	candidate	localmaxxing
Intel Arc Pro B60	llama.cpp	Q8_0	195 tok/s @ 4,096	candidate	localmaxxing

From local-ai-registry (MIT), commit 124959d: 2 runs across 2 machines, 0 validated — model revision and runtime pinned, launch accepted — and 2 candidate, their label for useful evidence without a reproducible-launch promise.

Elsewhere in the registry

All models → Browse with filters → What will run on my hardware? →

Registry record as of 2026-09-26. Identity, licence and parameter count are properties of a release and do not move; tier can, and the verify link above re-checks it against the live registry rather than this page.