Llama 3.2 (3B Instruct)
Llama · ~3B parameters · Under 4B · Last reviewed 2026-03-20
Why we use it
Strong latency and footprint for edge pilots and on-device demos while staying inside common enterprise acceptable-use policies when self-hosted.
License summary
Released under Meta’s Llama license with acceptable-use and attribution requirements; verify current terms on Meta’s site before redistribution.
Typical deployment profiles
- Edge / low footprint
- VPC, single GPU class
Focus tags
- General
- Multilingual
Typical use cases
- Triage bots
- On-VPC assistants
- RAG prototypes with small context