Verify critical details — pricing, licensing, availability — with the model's source before business decisions. Full methodology →
Llama 3.2 1B (Base)
Model family: llama-3-2
Base pretrained variant of Meta's smallest Llama 3.2 model. Text-only, 1.23B parameters, designed for on-deviceRunning a model directly on a consumer device — a laptop, a phone, a smart speaker — rather than in a data center. On-device inference keeps data private by never leaving the device, and works offline. Small models (under ~10B parameters, often quantized) can run on-device; larger models cannot yet. and edge deployment. For fine-tuning rather than direct chat use.
Identity
- Creator
- Meta
- Model family
- llama-3-2
- Release date
- 2024-09-24
Technical specs
- Parameter count
- 1.23B
- Context window
- 131K tokens
- Modalities
- Text
- Primary capabilities
- Chat
- Instruction Following
- Multilingual
License
- License
- Llama 3.2 Community License
- Commercial use
- Conditional
Free for commercial use unless the licensee's product has 700 million monthly active users at the Llama 3.2 release date (September 25, 2024), in which case a separate Meta license is required.
- Terms
- Modification ✓
- Redistribution ✓
- Attribution ✓
Access
- Openness
- Open Weight
- Access methods
- Local Runtime Llama Cpp
- Local Runtime Mlx
- Local Runtime Ollama
- Weights Download Direct
- Weights Download Hf
- Cost tier
- Mixed
- llm
- open-weight
- commercial-friendly
- small
- on-device
- long-context
- multilingual
- us-based
- base-model