RedHatAI/Qwen2.5-32B-Instruct-FP8-dynamic is a quantized variant of Alibaba's Qwen2.5 32B parameter instruct model. It supports chat, instruction following, and tool/function calling through a custom chat template. The model is provided as open weights on Hugging Face for use with the Transformers library or compatible inference providers.
Qwen2.5 32B Instruct FP8 Dynamic sits in PulseGate's Foundation models & chat category. It focuses on running large language models with reduced memory and compute requirements while maintaining instruction-following and tool-use capabilities. Qwen2.5 32B Instruct FP8 Dynamic is an open-source project aimed at developers. Qwen2.5 32B Instruct FP8 Dynamic is open source under the Open Source license. It runs on the web and API.
Behind Qwen2.5 32B Instruct FP8 Dynamic is RedHatAI, and it first shipped in 2024. It operates in a well-populated space: PulseGate tracks 13 similar projects. Key capabilities include Instruction Tuning, Tool Calling, and Quantized Inference.
Summary written by a language model from the project’s public pages.
What PulseGate has recorded for this listing
Closest matches by what these projects do