Edge0 open-sources streaming MoE framework with 35B and 8B on-device models
EAccelerate_42 · x · 2026-09-10
Edge0 is now open source, shipping 35B and 8B models plus local runtime and inference code built for phones, laptops, PCs and robots — fast, private, fully on-device. The streaming MoE framework combines SSD expert offload, Recover-LoRA and prerouter routing prediction, with a decoupled backend design: the current MLX backend targets Apple Silicon, and CUDA and other platforms plug into the same core abstractions. edge0-35B-A3B runs 4-bit with 40 layers and 256 experts (prerouter K=4); edge0-8B-A1B runs 4-bit with 24 layers and 128 experts (K=8). Checkpoints, LoRA adapters and prerouter heads are released as end-to-end units. The repo is new, with 88 stars so far.
Related event: Edge0 Open-Sources On-Device MoE Framework with 35B Model(2 posts)→
More from Infra
- Massachusetts to require 25MW+ data centers to provide clean power or fund ratepayer protection — rohanpaul_ai · 2026-09-10
- Massachusetts orders data centers over 25MW to bring their own clean power — rohanpaul_ai · 2026-09-10
- Meta signs deal for tens of millions of AWS Graviton cores to power agentic AI — bookwormengr · 2026-09-10
- iPhone 18 Pro's variable aperture: Apple returns to physics after hitting compute wall — r0ck3t23 · 2026-09-10
- Google Commits €13B to Finnish AI Data Centers, Its Largest European Investment — 创业邦 · 2026-09-10
- Flux 2 Klein image model now runs fully in the browser via WebGPU — radamar · 2026-09-10