Flash Attention | Local Model Watch

ExLlamaV3 1.4.8 Released: VRAM and FA2 Updates

September 7, 2026Engines and Tools

ExLlamaV3 1.4.8 Released: VRAM Opt & FA-2 Removal

October 31, 2026

ExLlamaV3 1.4.8 is released. Key updates include VRAM allocation optimization and the complete removal of Flash Atten ...

About Local Model Watch

Local Model Watch is a reference site, in English and Japanese, for open-weight generative models (text, image, video and audio) you can run on your own hardware: articles on new releases, hub pages, and measurements we take by running models on our own server. Memory requirements in every article are computed by this site from the actual distributed file sizes.

Start here