Replying to @sahajsarup
Qualcomm's lawyers are the company's biggest roadblock to growth.
The eye on that thing...
The technology powering tomorrow's AI is already taking shape.
Get an early look at Synopsys PCIe PHY IP built for the upcoming PCIe 8.0 standard, a foundational piece that will help future AI, storage, and networking systems move data faster than ever. Learn more: bit.ly/4yB4YHp
Replying to @pratiksharda2
We color coded it. You can also switch to IO view that shows every pinmux and electrical details of all the pins.
We will be rolling out interactive layouts for all Libre Computer boards: layout.hardware.libre.comput…
Replying to @System64fumo
We have an entire inference engine. 🤣
Replying to @sbccompare
We are working on a new light weight desktop as well on mutter.
Replying to @sbccompare
We are currently putting Renegade through it's paces. So many features.
Replying to @sbccompare
Every codec supported including encoding, faster graphics, 2D acceleration, video pipeline improvements, and more.
Replying to @sbccompare
DDR4 hit $20/GB. The board is $25 for the 512M and $35 for the 1GB. However we have the mother of all software updates landing next month with linux 6.18.y stable.
Replying to @geerlingguy
Dense ~30B models (needing 40GB VRAM) is where local inferencing becomes useful. GB10's 256b DDR inferface is the bottleneck that prevents it from being useful. RTX Pro 6000 is the real starting point. This may change with model advancements a year from now.
Replying to @will_whang
We have an ASUS with Snapdragon X Elite. What a nightmare machine.




