Guanaco (13B) overview
Guanaco (13B) by University of Washington NLP
Guanaco-13B: Open-source multilingual chatbot model based on LLaMA, efficient 4-bit QLoRA fine-tuning, competitive benchmark performance.
Guanaco (13B) specs
- Developer
- University of Washington NLP
- Input
- Text
- Output
- Text
- API
- OpenAI-compatible, base URL
https://api.aimlapi.com/v1
Guanaco (13B) Description
- Developer/Creator: Tim Dettmers
Overview
The Guanaco-13B is an open-source, fine-tuned language model developed for creating high-quality, multilingual chatbots. It is based on the LLaMA base model and offers competitive performance with commercial systems like ChatGPT and BARD.
Key Features
- Open-source for research purposes
- Efficient 4-bit QLoRA fine-tuning on the OASST1 dataset
- Available in multiple sizes: 7B, 13B, 33B, and 65B parameters
- Multilingual support, though primarily in high-resource languages
Intended Use
Guanaco-13B is intended for researchers and developers looking to experiment with and create multilingual chatbots. It allows for cheap and local experimentation with high-quality chatbot systems.
Language Support
Guanaco-13B supports multiple languages, with a focus on high-resource languages. The model's multilingual capabilities are achieved through fine-tuning on the OASST1 dataset.
Architecture
Guanaco-13B is built upon the LLaMA base model, with LoRA (Low-Rank Adaptation) adapters added to all layers. The rank of the LoRA adapters is set to 64.
Use cases
- building multilingual chatbots for customer support, education, and interactive assistants
- open research and experimentation in instruction-following language models
- creative writing with role-playing and storytelling capabilities
- generating detailed answers in multi-turn dialogues across languages
- multimodal question answering involving images and text
- language translation and interpretation
- cost-efficient local deployment for AI applications requiring high-quality language understanding
Capabilities
- Function calling
- Streaming
- Structured outputs
Guanaco (13B) API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $0.315 | 1M tokens |
| Output | $0.315 | 1M tokens |
Guanaco (13B) is deprecated on AI/ML API. The rates apply to existing integrations; the models below are current alternatives.
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Guanaco (13B) vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Guanaco (13B) | $0.315 | $0.315 |
 Seed 1.6 Flash | $0.0794 | $0.3174 |
 Ministral 3 8B 2512 | $0.3174 | $0.3174 |
| Voxtral Small 24B 2507 | $0.1058 | $0.3174 |
 gpt-oss-safeguard-20b | $0.0794 | $0.3174 |
Models similar to Guanaco (13B)
Related articles
Guanaco (13B) FAQ
Does Guanaco (13B) support streaming?
Yes, Guanaco (13B) can stream responses as they are generated.
Does Guanaco (13B) support tool calling and structured outputs?
Yes, Guanaco (13B) supports both function calling and structured outputs.
Who created Guanaco (13B)?
Guanaco (13B) was built by University of Washington NLP.