Today, we're introducing Mach-1 Additive, a 35 billion parameter model that can inference without ever multiplying by a weight. At 1.7 bits per weight, Mach-1 recovers 95% of the performance of the original full precision model, Qwen 3.6 35b, across 12 agentic and reasoning
Run Private AI agents 24/7 to increase your daily productivity.
Earn rewards running your web3 node at home.
Zero hassle, it just works dappnode.com
- What's the last thing you couldn't do because you didn't want to send data to OpenAI / Anthropic?What’s the last thing you couldn’t do because you didn’t want to send data to OpenAI / Anthropic?
- So incredibly thankful for your @OctantApp support! Still 9h for you to assign rewards or donate ETH directly to get HEAVILY matched by Octant! Help us remain Free and Open Source Forever!2 ETH! You made it you crazy fools, 2 ETH! And we still got some extra time!



