Morning Edition · Tuesday, August 4, 2026Published at 2:03 AM EDT · New York
An Open-Source Runtime Puts an 80-Billion-Parameter Qwen Model on a Mac in 4.3 Gigabytes of Memory
Swiftlet keeps only the dense core resident and streams routed experts from storage. It runs a 35-billion-parameter model on an iPhone 17 at roughly one token per second.
A Swift and Metal runtime called Swiftlet, published this week, targets the mixture-of-experts models in the Qwen3-Next and Qwen3.5/3.6 families and exploits a structural fact about them. Only a small fraction of the weights participate in…
Continue the AI Intelligence Brief
Track frontier labs, chips, export controls, model releases, regulation, and AI infrastructure.
- 5 AI intelligence signals a day
- Frontier labs, compute, and chips
- Model releases and AI infrastructure
- Source-grounded analysis with confidence labels
The Global Intelligence Brief stays free.
Part of a tracked trend
AI Inference Shifts to Consumer Devices
Over the next 3-6 months, smaller efficient architectures and inference-cost optimizations push capable AI off the cloud and onto laptops, phones, and mobile NPUs.
More from this edition
- Alibaba Ships Qwen3.8-Max, a 2.4-Trillion-Parameter Model It Promises to Open-Weight Next Week
- OpenAI Publishes Lean-Verified Proofs From Its Astra Model for Ten Long-Open Mathematics Problems
- Tencent's Hyra Agent Reports Beating the Historical Best on 29 of 55 Open Mathematics Problems
- Meta Puts Muse Image and a Muse Video Preview Into Its Consumer Apps With Conversational Editing
- Meta's Open Vision Models Move Into a $41.5 Million Robotic Wheelchair Program and Berkeley Lab Science
- AI Evaluation Turns Into a Product Market as Researchers Show Cheap Open Models Can Grade Proofs
- New Benchmarks Target the Decision Agents Make Before They Answer
- Agent Observability Reaches Cloud Consoles as Enterprises Report Measured Deployment Results
- Researchers Propose a Zero-Trust Registry for Agent Skills After Finding Claims Do Not Match Capabilities
- A Self-Refining Agent Takes On OpenFOAM Configuration, One of Engineering's Reliable Time Sinks
- A Paper Revives Leibniz, Turing and Searle to Argue Consciousness Tests Belong in AI Safety Work
Comments
0No comments yet.