Vicuna
Fine-tuned LLaMA model by LMSYS achieving 90% ChatGPT quality.
About
Vicuna by LMSYS is a chatbot model fine-tuned from LLaMA on user-shared ChatGPT conversations, which reached roughly 90 percent of ChatGPT quality in early automated comparisons and helped establish open chat models. It is distributed through the FastChat platform for training, serving, and evaluation in 7B and 13B sizes. Use follows the underlying Llama model 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
- Intermediate (3/5)
- License
- Llama License
- Minimum VRAM
- 8 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.