Phi-3
Small language model by Microsoft in 3.8B size with strong benchmark performance.
About
Phi-3 is a family of small open-weight language models from Microsoft, distributed in Mini (3.8B), Small (7B), and Medium (14B) sizes with 4K and 128K context variants. The models are trained on a curated mix of synthetic data and filtered web content aimed at reasoning density and benchmark performance for size class. Post-training combines supervised fine-tuning and DPO for instruction following. Released under the MIT license.
Reviews (0)
Leave a Review
No reviews yet. Be the first to review!
Details
- Category
- Large Language Models (LLMs)
- Price
- Free
- Platform
- Local/Desktop
- Difficulty
- Easy (2/5)
- License
- MIT
- Minimum VRAM
- 4 GB
- Added
- Apr 3, 2026
Related Tools
Open-source code LLM family by IBM for enterprise code generation.
High-performance open-weight MoE LLM with 671B total parameters.
Hybrid SSM-Transformer model by AI21 Labs combining Mamba with attention layers.
State-space model for language with linear-time sequence modeling.
Family of small language models by Hugging Face for on-device use.
Open-weight LLM by Meta in 8B and 70B sizes with strong general capabilities.