Research
70% Size, 100% Accuracy KV Cache is 1 Bit Per Channel NoMAD-Attention Accelerating Inference Sketch to Adapt
Contact
Blog
Llama Agents

model-release

Home
model-release

Meet the xMADified Gemma 2 (9B): High Performance, Minimal VRAM 🚀

Meet the xMADified Gemma 2 (9B): High Pe...

xMAD.ai

By xMAD.ai

Date

Nov 01 2024

support@xmad.ai

Terms

Terms of Use
Privacy Policy

Support & Help

Open Support Ticket

©XMAD.AI 2024, ALL RIGHTS RESERVED.