Own your AI. Agents that remember, execute code in isolated VMs, and stay reachable from anywhere -- all on your Mac. Any model. No cloud required. Open source.
Meet Gemma 4 12B!
A unified, encoder-free multimodal model designed to bring high-performance intelligence directly to your laptop, and released under an Apache 2.0 license.
Bridging the gap between edge efficiency and advanced reasoning. Here is whatโs new with Gemma 4 12B: ๐
@LiquidAI said device-optimized.
So I put it in airplane mode.
Read my files. Parsed a PDF. Pulled the contact. Zero internet.
LFM2.5-8B-A1B. ~100 tok/s.
@Camcamera11@atlas_cloud_ai Everything else stays local. You can point inference to a local model for full privacy. If you point to the cloud model, it will only send what is passed through inference, and you can scrub personal information using our built-in privacy filter.
@OsaurusAI ร Atlas Cloud integration is now live.โก๏ธ
OsaurusAI is an open-source, Swift-native AI agent framework for macOS โ local-first, so your data and agent context never leave your machine.
๐And you can use Atlas Cloud's LLM API in Osaurus now.
#Osaurus#AtlasCloud #AIIntegration #Swift #macOS #API #AItool #Opensource
gave @MiniMax_AI M3 one prompt:
build an idle game called "NEED MOAR COMPUTE."
it one-shotted a full frontier lab simulator. planned it, wrote it, ran it in a sandbox, tested its own code.
a model building a game about needing more compute.
asked it to build an idle game called "NEED MOAR COMPUTE."
one-shotted a full frontier lab simulator.
a model building a game about needing more compute.
MiniMax M3 running through Osaurus in an isolated sandbox.
It planned the build, wrote one HTML file, ran it, and verified its own JS and HTML before surfacing it.
Real 38 KB file. Playable.