Edge0-145B: How a 145B-Parameter Model Fits on One RTX 5090
Edge0-145B packs 145 billion parameters into 24GB VRAM using native 4-bit quantization and a sparse MoE design. Here's how it works.
MindStudio Blog7 min read
2 stories
Edge0-145B packs 145 billion parameters into 24GB VRAM using native 4-bit quantization and a sparse MoE design. Here's how it works.
Edge0-145B is a 145B-parameter sparse MoE model quantized to NVFP4, built to run locally on a single 24GB consumer GPU for agent tasks.
Showing 2 of 2 stories
You're all caught up.
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts