MLX

Specifications

No specifications recorded yet.

Latest developments

From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon BAIR · 5 days ago · 20 Nativ: Run AI models locally on your Mac Simon Willison · 1 week ago · 45 BaseRT provides faster runtime for serving AI models with less infrastructure The Neuron · 2 weeks ago · 9

SmolVLM2: Bringing Video Understanding to Every Device Hugging Face Blog · 1 year ago · 18

Q3 2026

• 29 Jul From CUDA to MLX: How K-Search Brings Decades of Kernel Expertise to Apple Silicon
• 21 Jul Nativ: Run AI models locally on your Mac
• 20 Jul BaseRT provides faster runtime for serving AI models with less infrastructure

Q1 2025

• 20 Feb SmolVLM2: Bringing Video Understanding to Every Device

Relationships

Products & technology

• Integrated with Metal · 1 source
• K-Search integrated with this model · 1 source
• Nativ integrated with this model · 1 source