Meet Titania – Axelera AI’s power-efficient AI chiplet, scaling seamlessly from edge to cloud. Built on Digital In-Memory Computing & RISC-V, Titania redefines AI acceleration. Find out everything, right here: https://
eu1.hubs.ly/H0hk8hx0 #AI #EdgeAI #RISC-V
HARDWARE
-
Titania: Axelera AI’s Power-Efficient Edge-to-Cloud Chiplet
By
–
-
Alibaba QwQ-32B: Reasoning AI Matches DeepSeek-R1 Cheaper
By
–
Alibaba’s Qwen team dropped QwQ-32B, a reasoning AI that matches or surpasses DeepSeek-R1 at much less cost
— Rowan Cheung (@rowancheung) 6 mars 2025
—20x smaller than DeepSeek-R1
—Priced $0.20 per million input and output tokens
—Open-sourced under Apache 2.0
Here it is running on M4 Max:pic.twitter.com/J40JG0jGtCAlibaba’s Qwen team dropped QwQ-32B, a reasoning AI that matches or surpasses DeepSeek-R1 at much less cost —20x smaller than DeepSeek-R1
—Priced $0.20 per million input and output tokens
—Open-sourced under Apache 2.0 Here it is running on M4 Max: -
HeadInfer: Long-Context LLM Inference on Consumer GPUs
By
–
HeadInfer: Unlocking Long-Context LLM Inference on Consumer GPUs (Million-level Tokens)
*long-context inputs require large GPU memory.
*A standard LLM like Llama-3–8B requires 207GB of GPU memory for 1 million tokens — far beyond the capabilities of consumer GPUs like the RTX -
TSMC Announcement Signals US Strategic Shift in AI Hardware
By
–
Indeed. Just speaking about the US in light of the TSMC announcement, but this is not lost on me. Writing on it now.
-
QwQ-32B Matches DeepSeek R1 at 20X Smaller Scale
By
–
DeepSeek just got DeepSeek'd. QwQ-32B is on par with DeepSeek R1 671B but ~20X smaller. AGI will run on your computer. Then it'll run on your phone.
-
Apple’s New AI Computer Challenges Government Data Privacy Norms
By
–
Apple's iPad post yesterday was a miss. But they just dropped the best computer you can buy for AI. They're fighting literal governments to keep your data private. They even kneecap themselves to do it. For all their faults we don't appreciate them enough.
-
Meta PARTNR Demo: Insights and Challenges in Human-Robot Collaboration
By
–
By sharing some of the insights and challenges in developing the Meta PARTNR demo, we hope to contribute to the development of the next wave of innovation in human-robot collaboration. Research paper https://
go.fb.me/prlg14
Dataset and code https://
go.fb.me/k9dzc0 -
Apple Mac Studio 512GB: The Ultimate AI Computing Machine
By
–
Apple's 512GB Mac Studio is no joke. Forget that most PCs max out at 128GB. That's not even VRAM. At 512GB of unified memory you're competing with multiple 5-figure $ GPUs. This can run DeepSeek R1 and basically anything else. There is no better computer for AI.