Our biggest breakthrough in efficiency yet, the Framework Laptop 13 Pro with 20 hours of battery life. In Graphite. Linux-first with options for Ubuntu pre-installed. Featuring Intel® Core™ Ultra Series 3 processors, LPCAMM2 Memory, a new haptic touchpad, and a touchscreen display. Pre-orders for the Framework Laptop 13 Pro open now: frame.work

listen up ROCm and Vulkan builders. @FrameworkPuter just shipped me strix halo desktop, 128GB unified, landing on my desk tuesday. everyone keeps asking what actually runs on this thing beyond vendor charts and forum guesses. so i'm going to answer it properly. starting with big MoE models since massive total params on light active is the whole point of 128GB unified. if there's a specific model or quant you want tested on strix halo, reply and it goes in the queue.

Building a Breadboard in a @FrameworkPuter expansion card. Drop a small dev board in the socket, prototype in a slot of your dock. Any @seeedstudio #XIAO or compatible footprint fits. Protected 5V/3V3, breadboard pins, USB passthrough. Post: hwlab.io/blog/building-bread… #DockFrame

Finally had some time to spent with my beautiful @FrameworkPuter, specifically a beefed out Max 395 with 128GB of LPDDR5x-8000. Quest: get Qwen3-TTS to work as well as on my new M5 Max. I have 2 implementations with 3 backends for the inference engine. - macOS only MLX (using MLX C bindings in Rust) - macOS only GGML Metal implementation - cross-platform GGML Vulkan implementation Below table shows results for generating 20 seconds of German with a reference voice on the M5 Max (GGML Metal, MLX) and the Framework (GGML Vulkan). The Framework gives me basically the same performance as the M5 Max at less than half the price. I had to massage GGML a tiny little bit, as its 1D conv kernels for Metal and Vulkan weren't ideal for the Qwen3-TTS decoder architecture. The GGML engine is based on github.com/second-state/qwen… The MLX engine is based on github.com/second-state/qwen… I forked both of these (plus GGML) and did some performance work on the in the past 2 nights. Shitty forks: github.com/badlogic/ggml github.com/badlogic/qwen3-tt… github.com/badlogic/qwen3_tt… Now my @FrameworkPuter can serve the Pipi bots of all the kids in our hood! Caveat: concurrent TTS is realistically only working for 2 kids at a time. Pibot repo here: github.com/badlogic/pibot Making of here: mariozechner.at/posts/2026-0… Very happy!

Come by our Computex booth and let us know what we should build next!

Framework has a booth here! Dropped by, said hi, and also voted for them to come to Malaysia please 🙏 Btw, met  @SalemTechsperts ! Super nice guy, the greatest technician that's ever lived 👍

Our booth is bigger this year, which means we have some exciting demos to share👀at Booth N1005 @computextaipei

watch me unbox my framework desktop while @theo do my voiceover

New strategy to mitigate silicon pricing. We’ll tweet whatever you want for 20k.

We needed to make a second price update this month, for the 128GB config of Framework Desktop, since we sold through the inventory of LPDDR5x that we brought in earlier at lower costs. We still have inventory of 32GB and 64GB Desktop configs at the lower prices for now.