Vicuna-13B
by Various
We introduce Vicuna-13B, an open-source chatbot trained by fine-tuning LLaMA on user-shared conversations collected from ShareGPT. Preliminary evaluation using GPT-4 as a judge s
Apps
Vicuna-13B
Added 1 June 2026
Overview
Vicuna-13B is an open-source chatbot created by fine-tuning the LLaMA model on 70,000 user-shared conversations from ShareGPT. It provides a free, locally runnable alternative to proprietary chat assistants, with weights and code released publicly under a noncommercial license.
Best for
Best for
Researchers, hobbyists, and developers seeking a free, locally deployable chatbot for experimentation and noncommercial use.
Use cases
- Running a conversational AI assistant on local hardware without cloud dependency
- Experimenting with instruction-tuned language model research and fine-tuning
- Building custom chatbot applications with open weights and community tooling
Notes
Vicuna-13B is an open-source chatbot created by fine-tuning the LLaMA model on 70,000 user-shared conversations from ShareGPT. It provides a free, locally runnable alternative to proprietary chat assistants, with weights and code released publicly under a noncommercial license.
Use cases
- Running a conversational AI assistant on local hardware without cloud dependency
- Experimenting with instruction-tuned language model research and fine-tuning
- Building custom chatbot applications with open weights and community tooling
Pros
- Open-source weights and code enable full transparency and customization
- Trains on real user conversations, producing more natural dialogue than synthetic data models
- Can run on consumer GPUs, lowering the barrier to deployment
Cons
- Noncommercial license restricts use in for-profit or corporate products
- Performance lags behind larger commercial models like GPT-3.5 or GPT-4
- Dependent on user-shared conversation quality, which can introduce inconsistency or bias
Indexed from awesome-generative-ai and enriched against its public facts.
Pros
- Open-source weights and code enable full transparency and customization
- Trains on real user conversations, producing more natural dialogue than synthetic data models
- Can run on consumer GPUs, lowering the barrier to deployment
Cons
- Noncommercial license restricts use in for-profit or corporate products
- Performance lags behind larger commercial models like GPT-3.5 or GPT-4
- Dependent on user-shared conversation quality, which can introduce inconsistency or bias
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.