← All companies
Generate ideas →
Apple
Exla
ActiveAn SDK to run transformer models anywhere
Winter 2025Founded 20252 peopleSan Francisco, CA, USA
About
Exla aggressively quantizes AI models to minimize memory usage and maximize inference speed. Whether you're deploying LLMs, VLMs, VLAs, or custom models, Exla reduces memory footprint by up to 80% and accelerates inference by 3–20x - all with just a few lines of code. https://cal.com/exla-ai/schedule
Founders · 2
Pranav NairCo-Founder
CTO at Exla. Previously an OS engineer at Apple leading sleep/hibernation for all Apple devices. B.S. Computer Science from Purdue.
AmazonB2BEngineering, Product and DesignArtificial IntelligenceEdge Computing SemiconductorsComputer Vision
Related startups
SF TensorFall 2025
Infrastructure for AI labs to focus on research.
Active
Talking ComputersWinter 2026
AI for AI Infrastructure
GPU Infrastructure OptimizationActive
