Browse Comments — Raw (as collected)

Close reading of the corpus at each pipeline stage: raw → clean → relevant → coded.

↓ Export filtered CSV
Reading comments under one post — MOHSIN ALI · General AI Discourse
Lisa Su just unveiled the world's smallest AI development PC. Built by AMD. Small enough to sit on your desk. Capable of running 200 billion parameter models locally. No cloud. No server farm. No d…
✕ clear post filter  ·  ← all posts
✕ Clear
42 comments matched  ·  page 2 of 3
Everything will move this direction. Local models running for regulated industries and those seeking privacy for IP security. It is the same reason Punky Tiger Labs created the PCIe card to turn any desktop PC into an AI machine. https://nymphtech.com
Fractional GTM & Growth Strategist | He… ⌕ thread
NPU!
Architecture. Content creator. Builder.… ⌕ thread
What feels impossible today often becomes normal surprisingly fast in technology. The pace of AI hardware advancement right now is honestly incredible.
Interior Design & Space Management | Hi… ⌕ thread
Lisa, Welcome to the fringe researcher community... let me show you where we keep the coffee.
Founder & Chief Architect @ Vector Labs… ⌕ thread
Xcllent hope 2050 we will have npu kid ppu pico processing unit
blinkit delivery partner ⌕ thread
Daniel Choi
Experienced Technical Leader & AI Innov… ⌕ thread
Press X for doubt
IsoMythric Systems B.v. | Paapst Group … ⌕ thread
I want this
I build software that moves money | Exe… ⌕ thread
A breakthrough moment
Applied Mathematics • Python Developmen… ⌕ thread
Godfrey Jeremiah While it can be used for training if time is not a constraint, training is not the primary purpose of these devices. These compact units are excellent for rapid prototyping projects and for building foundational blocks at a very low cost. They are scalable to a certain extent and provide a strong sandbox environment with all the necessary tools to get a project off the ground. I personally own one of these systems, not the AMD-based one, and it represents an interesting low-cost entry point. The strategy behind these little guys is to influence the market into dipping their toes into Ai.
Lenovo Workstation Specialist | Solutio… ⌕ thread
Saiful Said the cousins will keep surprises coming and engagement high
Making sure business responds, whenever… ⌕ thread
Godfrey Jeremiah I guess we are only capable of running the LLM, not to train them in that device. to train we still need large GPU infrastructure.
AI Product Leader & Practitioner | GxP … ⌕ thread
how much is it
NTU Computer Engineering | AI Product E… ⌕ thread
Fred Ramirez III i just posted an article breaking down how we do it at a high level. https://www.linkedin.com/pulse/we-just-compressed-10-ai-models-541-gb-down-38-kb-fred-ramirez-iii-6sckc/
AI/ML Engineer | LLM Fine-Tuning · Dist… ⌕ thread
https://www.linkedin.com/pulse/we-just-compressed-10-ai-models-541-gb-down-38-kb-fred-ramirez-iii-6sckc/
AI/ML Engineer | LLM Fine-Tuning · Dist… ⌕ thread
Mammie A Ross using an Outlook email is suspect.
Future of Work Architect | Building AI-… ⌕ thread
Q4 or FP16? If Q4 it's just bragging about Gigabytes...
Generalist / Agile Mindset / Servant Le… ⌕ thread
Did Jenson evolve into a woman?
Systems Architect | Independent Researc… ⌕ thread
Amazing!
Master’s in Computer Software Engineeri… ⌕ thread
cost?
Aspiring Godfather 🚬 · I Created legali… ⌕ thread
← Prev 1 2 3 Next →