Meta · Text · Released Sep 2024
Llama 3.2 1B
Meta's 1B instruction-tuned model — the smallest Llama, runnable in-process via HuggingFace or through Ollama.
Meta's Llama 3.2 1B is an open-weight text model. It takes a text prompt and replies with generated text. It runs entirely on your own hardware through Ollama and Hugging Face: no API key and no per-use fees.
Modality
Text
Available on
OllamaHugging Face
Model ID
ollama:llama3.2:1bhf:onnx-community/Llama-3.2-1B-Instruct-ONNX
Supported OS
macOSWindowsLinux
Minimum machine configuration
8 GB RAM · 128K ctx · text · CPU/GPU
Download size · ~1.3 GB
Specs
- Released
- 1 year ago (Sep 2024)
- Pricing
- Free, runs on your hardware
About the creator
Meta
Meta's FAIR and GenAI labs build the open-weight Llama family of language models — among the most widely used open models for local inference.
ai.meta.com ↗More from Meta
Llama 3.1 8B
TextLocal
Meta's 8B instruction-tuned model with 128K context and strong general reasoning.
Llama 3.2 3B
TextLocal
Meta's compact 3B instruction-tuned model — fast on-device text generation.
Muse Glimmer
TextLocal
Meta Superintelligence Labs' 30B multimodal model for always-on local agents — tuned for tool use, long tasks, and failure recovery.