Space V3.2 -

You get faster inference and lower hardware requirements without sacrificing the model's "brainpower." 2. Intentional Post-Training Scaling

The standout feature of v3.2 is its architectural efficiency. By combining with Multi-Head Latent Attention (MLA) , the model significantly reduces the computational cost of long-context processing. Space v3.2

Eos v3.2 introduces Augment3d Zones , allowing your 3D model space to automatically control fixture behavior based on location. You get faster inference and lower hardware requirements