FreeToken Enables 35B Models on 8GB Laptops via Unified CPU-GPU Memory

mark_k · x · 2026-08-23

FreeToken is a software breakthrough for local AI that intelligently coordinates GPU, CPU, and system RAM to dynamically move MoE experts where needed, eliminating the requirement for enough VRAM to hold an entire model.

Benchmarks show an ordinary laptop with an 8GB RTX 4060 running a 35B model at 39 tok/s, while a gaming PC with an RTX 5090 can interactively run a massive 284B DeepSeek model. This allows users to run powerful AI on existing hardware without API costs or cloud dependency.

Related event: UC Berkeley and MIT Open-Source FreeToken: Frontier MoE Models on Consumer PCs(11 posts)→

Original post →

More from Infra

Infra channel →