diffusiongemma-26B-A4B-it-FP8-dynamic is an instruction-tuned diffusion model from RedHatAI that combines Gemma language understanding with diffusion-based image generation. The FP8 dynamic quantization enables more efficient inference while maintaining generation quality. It is published on Hugging Face for local or hosted use.
In the Foundation models & chat space, Diffusiongemma 26B A4B It FP8 Dynamic takes a focused approach. It focuses on generating high-quality images from text prompts using an efficient quantized diffusion model. It is built as an open-source project for developers. Diffusiongemma 26B A4B It FP8 Dynamic is open source under the Apache-2.0 license. It runs on the web and API.
RedHatAI builds and maintains Diffusiongemma 26B A4B It FP8 Dynamic, and the product first shipped in 2019. Development happens publicly on GitHub with 3.6k stars and 164 commits in the last 90 days. It operates in a well-populated space: PulseGate tracks 7 similar tools. Key capabilities include text-to-Image, diffusion, and FP8 Quantization.
Latest indexed changes and source events
RedHatAI/diffusiongemma-26B-A4B-it-FP8-dynamic verified by the PulseGate indexer
