No longer supported

This model is legacy (released May 2023) and is no longer actively maintained or recommended by Stability AI. Consider using their current flagship model instead.

legacylegacyllm Open Source

Stable LM 3B

by Stability AI· Released May 2023· Cutoff May 2023

Stable LM 3B is a compact 3 billion parameter language model developed by Stability AI, designed for efficient text generation on consumer hardware. It is part of the Stable LM family, offering a lightweight alternative to larger models while maintaining strong performance for its size. The model is open-source and suitable for fine-tuning and deployment in resource-constrained environments.

Official Site 🤗 Hugging Face

Input cost

Free (open source)

Output cost

Free (open source)

Context window

4096 tokens

Max output

—

Modalities

text

Parameters

License

Apache-2.0

Capabilities

Text GenerationCode GenerationFine-tuningStreaming

Best For

Efficient text generation and fine-tuning on consumer hardware with limited resources.

Strengths

Compact size enables local deployment on consumer GPUs
Open-source with permissive license
Good performance for its parameter count
Supports fine-tuning for custom tasks

Limitations

Smaller context window (4096 tokens)
Lower accuracy compared to larger models
Limited multilingual support
No vision or multimodal capabilities

Use Cases

Chatbots and virtual assistants on edge devices

Code completion and generation in IDEs

Text summarization for personal use

Educational tools for language learning

Rapid prototyping of NLP applications

Fine-tuning for domain-specific tasks

Offline text generation on laptops

Back to all models

No longer supported

This model is legacy (released May 2023) and is no longer actively maintained or recommended by Stability AI. Consider using their current flagship model instead.

legacylegacyllm Open Source

Stable LM 3B

by Stability AI· Released May 2023· Cutoff May 2023

Official Site 🤗 Hugging Face

Input cost

Free (open source)

Output cost

Free (open source)

Context window

4096 tokens

Max output

—

Modalities

text

Parameters

License

Apache-2.0

Capabilities

Text GenerationCode GenerationFine-tuningStreaming

Best For

Efficient text generation and fine-tuning on consumer hardware with limited resources.

Strengths

Compact size enables local deployment on consumer GPUs
Open-source with permissive license
Good performance for its parameter count
Supports fine-tuning for custom tasks

Limitations

Smaller context window (4096 tokens)
Lower accuracy compared to larger models
Limited multilingual support
No vision or multimodal capabilities

Use Cases

Chatbots and virtual assistants on edge devices

Code completion and generation in IDEs

Text summarization for personal use

Educational tools for language learning

Rapid prototyping of NLP applications

Fine-tuning for domain-specific tasks

Offline text generation on laptops

Back to all models