By
–
Now all I need is an easy way to get all of these action figures into printable 3D assets and use the @BambulabGlobal A1 printer to actually print these. https://t.co/k3jwN0FLag
— Linus ✦ Ekenstam (@LinusEkenstam) 1 avril 2025
Now all I need is an easy way to get all of these action figures into printable 3D assets and use the @BambulabGlobal A1 printer to actually print these.
By
–
In the machine or print? This is the DJI of 3D printers. Everything just works, no need to fiddle with anything, zero hassels. community is massive. is the machine tinker friendly? nope.
By
–
What would you print? If you have a 3D printer what’s been the best thing you ever printed?
By
–
So I went ahead and printed some as a test. These 6 pieces came out while we had dinner and prepped for bedtime. pic.twitter.com/D1PKojvCRk
— Linus ✦ Ekenstam (@LinusEkenstam) 1 avril 2025
So I went ahead and printed some as a test. These 6 pieces came out while we had dinner and prepped for bedtime.
By
–
Was setting up this little A1 from @BambulabGlobal yesterday.
— Linus ✦ Ekenstam (@LinusEkenstam) 1 avril 2025
I was not expecting this insane print speeds to be honest
kids wanted some connectors for their hot wheels and Lego…. pic.twitter.com/Mvx4w4V5nR
Was setting up this little A1 from @BambulabGlobal yesterday. I was not expecting this insane print speeds to be honest kids wanted some connectors for their hot wheels and Lego….
By
–
Excellent summary Glen, Adoption of Advanced Technologies is such a strong example here. With the high-speed, low-latency capabilities of #5G rural factories can integrate advanced technologies such as #sensors and #drones These tools drive process improvements and modernize
By
–
Raw FPS ≠ real-world performance. If your pipeline can’t deliver end-to-end speed, even the fastest chip won’t help. Efficient #AI means optimising everything—hardware, software, and workflow. What matters most to you in AI at the edge? https://
eu1.hubs.ly/H0hSN-N0
By
–
Pretty well! TPUs are quite good for serving models like these, and we have awesome folks doing a great job of performance tuning to squeeze even more juice from them.
By
–
While the 4‑bit model experiences a 30–45% increase in inference time due to dequantization overhead, the output remains coherent and accurate. This approach makes deploying large models on resource-constrained hardware much more feasible.