cd /news/machine-learning/freetoken-efficient-edge-native-moe-… · home topics machine-learning article
[ARTICLE · art-106661] src=arxiv.org ↗ pub= topic=machine-learning verified=true sentiment=↑ positive

FreeToken: Efficient Edge-Native Moe Serving with Bandwidth-Adaptive Execution

Researchers introduced FreeToken, an edge-native Mixture-of-Experts (MoE) serving system that enables frontier-scale AI models to run on personal hardware, supporting over 20 MoE models and real coding and tool-using agents across devices from an 8GB laptop GPU to a single workstation GPU. The system expands practical serving from a 35B model on a laptop to a 284B model on a gaming desktop and the 753B GLM-5.2 on a single workstation GPU, turning open weights into deployable local software. FreeToken co-designs the full serving stack with bandwidth-adaptive execution to handle heterogeneous edge resources and continuously changing agent workloads.

read2 min views2 publishedAug 21, 2026
FreeToken: Efficient Edge-Native Moe Serving with Bandwidth-Adaptive Execution
Image: source
[Submitted on 17 Aug 2026]


[View PDF](/pdf/2608.16157)

[HTML (experimental)](https://arxiv.org/html/2608.16157v1)

Abstract:Frontier open-weight models are increasingly available, but serving them still largely assumes datacenter infrastructure. We present FreeToken, an edge-native MoE serving system that treats a personal machine not as a small GPU, but as a unified, elastic inference platform. FreeToken co-designs the full serving stack, including model layout and , expert residency, CPU--GPU execution, agentic state reuse, and runtime memory management, around two realities of local AI: agent workloads continuously change their execution pattern, and edge hardware exposes heterogeneous resources whose balance differs from machine to machine. Rather than committing to a fixed off strategy, FreeToken continuously maps computation and model state onto the resources actually available. FreeToken supports more than 20 MoE models and real coding and tool-using agents across hardware ranging from an 8GB laptop GPU to a single workstation GPU. More importantly, it changes what these machines can practically serve, from a 35B model on a laptop to a 284B model on a gaming desktop and the 753B GLM-5.2 on a single workstation GPU. FreeToken turns open weights into deployable local software, making the machines users already own a practical platform for frontier-scale intelligence. We release the system at[this http URL].

References & Citations

...

Bibliographic Explorer

(What is the Explorer?) Connected Papers

(What is Connected Papers?) Litmaps

(What is Litmaps?) scite Smart Citations

(What are Smart Citations?)# Code, Data and Media Associated with this Article alphaXiv

(What is alphaXiv?) CatalyzeX Code Finder for Papers

(What is CatalyzeX?) DagsHub

(What is DagsHub?) Gotit.pub

(What is GotitPub?) Hugging Face

(What is Huggingface?) ScienceCast

(What is ScienceCast?)# Demos Influence Flower

(What are Influence Flowers?) CORE Recommender

(What is CORE?)# arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

── more in #machine-learning 4 stories · sorted by recency
── more on @freetoken 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/freetoken-efficient-…] indexed:0 read:2min 2026-08-21 ·