Skip to content
← Models
Open weightsMeta/10 trustVerified

Llama-3.2-1B-Instruct

Meta's tiny 1B instruction-tuned model built for on-device chat and tool use.

Visit official page →

About

Llama-3.2-1B-Instruct is the instruction-tuned variant of Meta's 1-billion-parameter Llama 3.2 model, released on September 25, 2024 alongside the 3B, 11B vision, and 90B vision models. It was designed from the start for edge deployment, with a 128K token context window and day-one optimizations for Qualcomm, MediaTek, and Arm hardware.

The model supports instruction following, summarization, and rewriting tasks running fully on device, plus tool use through the Llama Stack distributions. Weights are downloadable under the Llama 3.2 Community License, a custom Meta license rather than an OSI-approved open source license, so commercial users should review its terms.

Specs

Context window

Pricing

Free quota

API access

Weights

Open weights

Released

September 25, 2024

Benchmarks

Provider-reported unless a source says otherwise. Benchmarks are marketing-adjacent by nature — treat them as directional.

Use cases

on-device-aichatbotsfunction-callingedge-inference

Trust score — 9/10

/10 trustVerified

Scored 9/10 (verified tier, metrics-v1). Evidence: Verified via vendor site/docs/GitHub and reputable coverage, wave 124; Trending score 88/100 from researcher assessment.

More in the llama family

Sources