teolm30/fox-1.6
TEXT GENERATIONConcurrency Cost:1Model Size:2BQuant:BF16Ctx Length:32kPublished:May 28, 2026License:apache-2.0Architecture:Transformer Open Weights Warm
Fox 1.6 is a compact, 2 billion parameter language model developed by teolm30, based on the Qwen3-1.7B architecture. Designed for general-purpose text generation, it is optimized for on-device or low-footprint inference. This model excels at assistant-style chat and completion tasks, making it suitable for rapid experimentation on consumer hardware.
Loading preview...
Fox 1.6: A Compact Qwen3 Fork
Fox 1.6 is a lightweight, 2 billion parameter language model developed by teolm30, forked from the Qwen/Qwen3-1.7B base model. It is specifically designed for general-purpose text generation with a focus on compact deployment and efficient inference.
Key Capabilities
- Compact Design: Built for on-device or low-footprint inference, making it accessible for consumer hardware.
- General-Purpose Text Generation: Capable of producing human-like text for various applications.
- Assistant-Style Chat & Completion: Well-suited for interactive chat applications and completing user prompts.
- Rapid Experimentation: Provides a solid, compact base model for developers to quickly test and iterate.
Intended Use Cases
- On-Device AI: Ideal for applications requiring local processing without heavy cloud reliance.
- Low-Footprint Inference: Suitable for environments with limited computational resources.
- Chatbots & Assistants: Can power basic conversational agents and automated response systems.
- Development & Prototyping: Serves as an excellent starting point for fine-tuning with custom instruction datasets to create genuinely new models tailored to specific benchmarks.