The release of int4 quantized versions of Gemma 3 models, optimized with Quantization Aware Training (QAT) brings significantly reduced memory requirements, allowing users to run powerful models like Gemma 3 27B on consumer-grade GPUs such as the NVIDIA RTX 3090.
Gemma 3 QAT Models: Bringing state-of-the-Art AI to consumer GPUs
Related Posts
Deep Dive into Scala 3 Macros: Building a Custom String Interpolator
This blog post explores the powerful macro system in Scala 3 through a practical example: a custom string…
SQL Subquery and CTEs( Common Table Expressions)
What is a subquery? Subquery is a query nested inside another query statement. It allows the query to…
Hacking Excel Files in Power Automate
Ever since 2003 Microsoft had to open up their Office files for other software, and that meant moving…
