Qwen2.5-3B-Instruct-GGUF provides the 3 billion parameter version of Alibaba's Qwen2.5 instruction-tuned model in GGUF format for use with llama.cpp and compatible engines. It supports advanced features including tool calling and follows a detailed chat template. The model offers a strong balance between performance and efficiency for local deployment.
Qwen2.5 3B Instruct is a Foundation models & chat product. It focuses on running a capable 3B instruction model locally with support for tool use and efficient quantization. It is built as an open-source project for developers building local AI applications. Qwen2.5 3B Instruct is open source under the Open Source license. The product ships for the web, the command line, and API.
Qwen builds and maintains Qwen2.5 3B Instruct, and the product first shipped in 2024. Development happens publicly on GitHub with 27.4k stars. The category is crowded — PulseGate's index counts 25 comparable apps. Key capabilities include Instruction Tuned, GGUF Format, and Tool Calling.
Latest indexed changes and source events
Qwen/Qwen2.5-3B-Instruct-GGUF verified by the PulseGate indexer
Other apps tracked under the same category.
