Llama 3.2 is available on Ollama! It’s lightweight and multimodal! It’s so fast and good! Meta’s Llama 3.2 goes small with 1B and 3B models.
The Meta Llama 3.2 series of multilingual large language models (LLMs) consists of pretrained and instruction-tuned generative models available in 1B and 3B parameter configurations (text in/text out). Optimized for multilingual dialogue, the Llama 3.2 instruction-tuned models excel in tasks like agentic retrieval and summarization, consistently outperforming many open-source and proprietary chat models on industry-standard benchmarks.
Model Sizes
3B Parameters (default)
The 3B model surpasses models like Gemma 2 (2.6B) and Phi 3.5-mini in areas such as:
- Instruction following
- Summarization
- Prompt rewriting
- Tool usage
To run: ollama run llama3.2
1B Parameters
The 1B model performs competitively with Gemma 2 (2B) and is well-suited for:
- Personal information management
- Multilingual knowledge retrieval
- Rewriting tasks on edge devices
To run: ollama run llama3.2:1b