Edge0-145B: open 145B MoE that runs on a single consumer GPU
Edge0 open-sourced 145B and 120B latent-MoE models derived from Qwen3.8-Flash-Next, plus an inference framework that runs the 145B model on one consumer GPU at a claimed 29GB peak memory and 80+ tokens/s.
Why it matters
First 145B-class open-weight model built to run on a personal machine instead of a data center, with about 10B active parameters per token.
What you could build with it
An indie developer could ship a private coding assistant that runs entirely on a single gaming GPU, keeping client code on the machine instead of sending it to a cloud API, and sell it as a one-time download to small studios.
Does it hold up?
Too early to judge — the weights and code are public and the repo passed 10,000 stars in a day, but every performance figure so far comes from Edge0's own tests; no independent benchmark has landed yet.
Built with Edge0-145B
- Edge0-145B: An open 145-billion-parameter model that's meant to run on your laptoptokenstrom.com · Breaks down the release and flags that every benchmark so far comes from Edge0 itself, not independent tests.
- Edge0 Says Its 145B Model Runs on a Laptop. The Weights Are Freemedium · Notes the repo passed 10,000 stars within a day and treats the launch as a free weekend experiment, not a purchase decision.
- Edge0-145B: Open 145B MoE for One GPU, Benchmarksai-tldr.dev · Fact-checked spec sheet: 145B total, about 10.12B active per token, 256K context, Q3_K and NVFP4 builds, Edge0 Community Model License.
Learn more
First spotted on article: source.
More AI models
VoiceStudio: open-source, fully-local ElevenLabs alternative for voice cloning, dubbing, and audiobooksdebpalash/VoiceStudio is a desktop app that runs voice cloning, voice design, video dubbing, dictation, transcription…models · JEV 0.75Strata: run a 125B model on a gaming PCFree, MIT-licensed local inference engine that runs Qwen3.8-Flash-Next (125B MoE, about 6B active per token) on…models · JEV 0.73Google AI Edge Gallery: offline speech recognition and synthesis on-deviceGoogle added fully offline speech recognition and text-to-speech to AI Edge Gallery, with ML Kit APIs on Android and…models · JEV 0.73Soup: fine-tune an 8B LLM on a 4 GB laptop GPU from one YAML fileAn open-source CLI that fine-tunes LLMs from a single YAML file, with layer streaming that trains an 8B model on a 4…models · JEV 0.73Tencent Hunyuan Hy3: open 295B MoE with 21B active under Apache 2.0Tencent open-sourced Hy3, a 295B-parameter mixture-of-experts model with only 21B parameters active per token, under…models · JEV 0.73NVIDIA Isaac Lab 3.0 GA + Isaac OS open runtime + Agile ONE SN humanoidMajor Isaac platform expansion at GTC Berlin Oct 21: Isaac Lab 3.0 is generally available as the open-source robot…models · JEV 0.73
Get the week's best AI launches, plus 3 ideas worth building
One email every Saturday. Ranked by traction, not hype. Free.