Framework

@FrameworkPuter • 107,922 subscribers

Remaking consumer electronics to respect people and the planet. 💻🪛 For support visit https://t.co/OcUxJ6ebU3

Shorts

312,303 views

37,319 views

76,490 views

138,558 views

69,493 views

52,029 views

Videos

sweetdream.ai

Watch Anya Live

Anya is streaming live right now! Join her private show and enjoy exclusive content.

Private Show

Join now for exclusive access

Free preview available • Premium content

592,541 views • 2 years ago

54,947 views • 2 months ago

83,104 views • 3 months ago

129,524 views • 10 months ago

345,156 views • 2 years ago

44,862 views • 3 months ago

118,474 views • 1 year ago

142,958 views • 2 years ago

29,573 views • 11 months ago

12,423 views • 1 year ago

No more content to load

Live Cam

Framework

Shorts

We delivered on generational graphics upgradeability in a laptop. The new Framework Laptop 16 with AMD Ryzen AI 300 Series processors, NVIDIA GeForce RTX 5070 graphics, and 240W USB-C power adapter is now live and available for pre-order!

One of the coolest uses of LM Studio and AI at AMD is using LM Link to have a Framework Desktop be a remote inference server for a laptop, including something little like Framework Laptop 12. It feels native on the laptop, but gets the desktop’s performance.

I made one important tweak to my Omarchy configuration

Today we also shared open source CAD of the surface of Framework Laptop 16, enabling development of skins, shells, replacement parts, and other accessories:

Today we opened shipping to Denmark, Sweden, and Finland! We're looking forward to reaching more of you as we go (and we're looking forward to the dozens of comments letting us know where to go next).

Not an April Fools Joke. Joseph Schroedl in the Framework Community built a batch of RGB LED Matrix Input Modules for Framework Laptop 16.

Videos

Watch Anya Live

Our Founder Nirav Patel walks through Framework's philosophy and the new products we launched today.

Google's new Gemma 4 is excellent, and the 26B MoE version is likely the best model to run on a 32GB Framework Desktop. It's fast, smart, and also great for tool calling if you use it with OpenClaw🦞 or other local agent platforms.

Interested in making Windows even less secure? You can run OpenClaw🦞 locally on Framework Desktop using LM Studio and AI at AMD and give it full control over your life!

The new gpt-oss-120b from OpenAI is now the best general purpose model to run on a Framework Desktop! ~40 tok/s on the MXFP4 version in LM Studio on Fedora 42.

We’re excited to share that Framework Laptop 16 pre-orders are now open, with configurations powered by the latest AMD Ryzen™ CPUs and AMD Radeon™ GPUs!

We found a great use case for OpenClaw🦞 running locally on a Framework Desktop with Fedora Project (@[email protected])!

Coming soon🩷💜💚🖤🤍

Fine! You asked for it!

128GB in Framework Desktop means you can run giant models locally like AI at Meta's Llama 4 Scout. This is a 109B MoE model with 17B active parameters. At Q6 this runs at &gt;14 tok/s on LM Studio on Fedora 42!

Help us make better content! We just opened a new full time Content Creator role based out of Framework HQ in SF.

128GB in Framework Desktop means you can run giant models locally like AI at Meta's Llama 4 Scout. This is a 109B MoE model with 17B active parameters. At Q6 this runs at >14 tok/s on LM Studio on Fedora 42!