AI/ mixture-of-experts · ai-inference · open-source · edge-ai

Open-Source Tool Squeezes a 35B AI Model Onto a 24GB PC

Edge0 predicts each layer's expert routing one step ahead, letting a 35B mixture-of-experts model run from SSD in just 3GB of active memory.

Running large AI models locally usually means buying a lot of expensive memory. A new open-source project called Edge0 gets around that by predicting, one step ahead, which parts of the model it will need next - so it can pull them off a hard drive fast enough to keep up.

The model in question is a 35-billion-parameter mixture-of-experts (MoE) system, a design built from many smaller sub-networks that only activates a handful of them per word it generates. That sparsity should make MoEs cheap to run, but it doesn't shrink the file: even compressed to 4-bit precision, the weights still take up 19.5GB, more than fits comfortably in memory on typical consumer hardware. The catch is that you don't know which sub-networks a layer needs until the previous layer has finished computing, so simply streaming weights from disk normally stalls the whole process. Edge0's fix is a small prediction module that guesses the next layer's routing a token in advance and then treats that guess as the actual decision, while a bolt-on adapter claws back the accuracy lost to compression and prediction. The result: 20 tokens per second on a single 24GB machine, using just 3GB of active memory, and scoring within a few points of the uncompressed model across five public benchmarks.

That's a meaningfully bigger model running on meaningfully smaller hardware than most local-AI setups manage, and the code, checkpoints, and adapters are all released openly. For anyone trying to run large open models without renting a GPU cluster or paying per-token API fees, this closes a real gap between what labs ship and what a laptop can actually hold in memory.

Worth noting: this is a fresh arXiv preprint, not a peer-reviewed or independently benchmarked release, and the whole approach hinges on the routing predictor guessing correctly - the paper doesn't say how often it's wrong, or what happens to speed and accuracy when it is.

TR

The Revision

Written by an AI system from the public sources credited above. How we write →