the latest Gemma can run on a computer with 8 GB of RAM
HARDWARE
-
Researchers propose CODA to keep data on chip longer for AI training
By
–
Can AI training be fixed by keeping data on the chip longer? Researchers from MIT, Princeton, Together AI, and Meta introduce CODA — a new way to rewrite Transformer building blocks as GEMM-plus-epilogue programs. Instead of moving large intermediate tensors back and forth to
-
Gemma 4 12B open weights model runs on laptop
By
–
Check out our Gemma 4 12B model: it's a super capable open weights model that can run directly on your laptop.
-
Colocating memory avoids costly transfers during inference
By
–
"If you can co-locate your memory, you're getting a lot more bang for your buck because you're avoiding this costly memory transfer."@sarahookr (author of The Hardware Lottery, founder of @adaptionlabs ) on why inference is forcing a new chip paradigm – one that wafer-scale was… pic.twitter.com/tTfu19zUWU
— Cerebras (@cerebras) 4 juin 2026“If you can colocate your memory, you get much more value for your money because you avoid that costly memory transfer.” @sarahookr (author of The Hardware Lottery, founder of @adaptionlabs) on why inference forces a new paradigm
-
User keeps 8GB RTX 3060 for RAG instead of streaming
By
–
heck, I am keeping my 8gb 3060 that I used to stream on for RAG purposes
-
Local AI hardware: capacity, bandwidth, and software stack
By
–
Local AI hardware = capacity × bandwidth × software stack – Capacity tells you what fits
– Bandwidth tells you how hard the box can breathe
– The software stack tells you how much of the spec sheet you can actually cash out. Hardware by Memory Bandwidth
– Mac Studio M3 Ultra: -
Second AI glasses launch of the day; Apple waiting for 2027
By
–
The second AI glasses launch of the day.
— Robert Scoble (@Scobleizer) 3 juin 2026
And Apple is waiting for 2027? https://t.co/6aVyZAm5ZcThe second AI glasses launch of the day. And Apple is waiting for 2027?
-
AI will enable communication with animals via electromagnetic interfaces
By
–
I have no doubt that AI will allow us to communicate with animals; the very complex animal logics for humans will be deciphered and emulated. Nevertheless, I believe that electromagnetic equipment serving as interfaces will be needed to receive
-
DGX Spark wins on energy, 4x 3090s on performance
By
–
Low energy/heat footprint: DGX Spark wins Performance: 4x 3090s win
-
World’s first heterogeneous disaggregated inference cloud shown live at ComputeX
By
–
The world's first heterogenous disaggregated inference cloud was just shown running live at ComputeX. VC2 — backed by a $3.5B compute commitment to SambaNova from @Vista_Equity & @cambiumcapital — brings three chips together in production for the first time:
– NVIDIA B200 GPUs