DawitShibabaw/llama-3.2-3b-instruct

TEXT GENERATIONConcurrent Unit Cost:1Model Size:3.2BQuant:BF16Context Size:32kTool Calling:SupportedPublished:Jul 10, 2026License:llama3.2Architecture:Transformer Featherless Exclusive Cold

DawitShibabaw/llama-3.2-3b-instruct is a 3.21 billion parameter instruction-tuned Llama 3.2 model developed by Meta. Optimized for multilingual dialogue use cases, it excels in agentic retrieval and summarization tasks. This model supports a 32768 token context length and is designed for commercial and research applications, outperforming many open-source and closed chat models on common benchmarks.

Loading preview...

Model Overview

DawitShibabaw/llama-3.2-3b-instruct is a 3.21 billion parameter instruction-tuned model from Meta's Llama 3.2 family, optimized for multilingual dialogue. It leverages an optimized transformer architecture and is fine-tuned using supervised fine-tuning (SFT) and reinforcement learning with human feedback (RLHF) to align with human preferences for helpfulness and safety. The model supports a context length of 32768 tokens and was trained on up to 9 trillion tokens of publicly available online data with a knowledge cutoff of December 2023.

Key Capabilities

  • Multilingual Performance: Officially supports English, German, French, Italian, Portuguese, Hindi, Spanish, and Thai, with training on a broader range of languages.
  • Dialogue Optimization: Specifically designed for assistant-like chat and agentic applications such as knowledge retrieval, summarization, mobile AI-powered writing assistants, and query/prompt rewriting.
  • Quantization Support: Includes quantized versions (SpinQuant and QLoRA) optimized for on-device use cases with limited compute resources, demonstrating significant improvements in inference speed and reduced memory footprint.
  • Robust Safety Measures: Developed with a three-pronged safety strategy, including responsible deployment guidelines, safety fine-tuning, and system-level safeguards like Llama Guard.

Good For

  • Multilingual Chatbots: Building conversational AI agents that operate across multiple languages.
  • On-Device AI: Deploying AI applications on mobile devices or other constrained environments due to its optimized quantized versions.
  • Agentic Applications: Tasks requiring knowledge retrieval, summarization, and intelligent prompt rewriting.
  • Research and Commercial Use: Intended for both academic research and commercial deployments, adhering to the Llama 3.2 Community License.

Finetunes
1 models