XHToken/Spark-X2.5
Spark-X2.5 is an open series of compact general-purpose language models (1.7B and 4B parameters) targeting on-device agentic use.
Collecting fresh signals — velocity needs a few days of history.
collecting data…
star history
The repository introduces Spark-X2.5-4B and Spark-X2.5-1.7B, compact transformer-based language models designed for on-device deployment. The models target conversation, writing, translation, reasoning, coding, tool use, and agentic workflows, with native context windows up to 1M tokens. The project is distributed across multiple inference runtimes including llama.cpp, MLX, vLLM, SGLang, and Ollama, and is published on Hugging Face and ModelScope.
Frequently asked
- What is XHToken/Spark-X2.5?
- Spark-X2.5 is an open series of compact general-purpose language models (1.7B and 4B parameters) targeting on-device agentic use.
- Is Spark-X2.5 open source?
- Yes — XHToken/Spark-X2.5 is open source, released under the Apache-2.0 license.
- How popular is Spark-X2.5?
- XHToken/Spark-X2.5 has 521 stars on GitHub.
- Where can I find Spark-X2.5?
- XHToken/Spark-X2.5 is on GitHub at https://github.com/XHToken/Spark-X2.5.