Qwen2.5-72B-Instruct-GGUF is a quantized version of the Qwen2.5-72B-Instruct large language model provided in GGUF format on Hugging Face. It is distributed by bartowski and supports a specific chat template for instruction following and tool calling. The template defines behavior for system prompts, defaulting to the identity of Qwen created by Alibaba Cloud as a helpful assistant, and includes structured XML-based handling for function calls with JSON arguments when tools are supplied.
The repository contains the necessary prompt formatting logic to enable the model to process messages, insert tool definitions within designated XML tags, and generate tool calls in a precise format enclosed in tool_call tags. This implementation allows the model to operate with one or more functions during inference. The GGUF format itself is intended to facilitate local execution through compatible engines.
It belongs to the class of foundation models released for open use. No pricing, licensing terms, or specific hardware requirements are stated in the page content.
In the Foundation models & chat space, Qwen2.5 72B Instruct takes a focused approach. It focuses on running large language models locally without relying on cloud APIs. Qwen2.5 72B Instruct is an open-source project aimed at developers. The project is open source (MIT). It runs on the web and the command line, and it can be self-hosted.
bartowski builds and maintains Qwen2.5 72B Instruct, and the product first shipped in 2023. The project is developed in the open on GitHub with 121.2k stars and 1.2k commits in the last 90 days. It competes in a saturated segment with 25 similar apps in PulseGate's index. Among its 4 catalogued features are GGUF Format, Quantized Weights, and Tool Calling.
Latest indexed changes and source events
bartowski/Qwen2.5-72B-Instruct-GGUF verified by the PulseGate indexer
Other apps tracked under the same category.
