Browse Comments — Clean (de-noised)

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
40 comments matched  ·  page 1 of 2
Awesome innovation 💕❤️💕Showcase @ Computex 2026. See ya 🥰
Fractional CTO & Innovation Architect. … General AI Discourse filtered out ⌕ thread
and?????
Future of Work Architect | Building AI-… General AI Discourse filtered out ⌕ thread
Corriente already has all llms runing on one dgx spark. We can compress 100TB down to 28MB
AI/ML Engineer | LLM Fine-Tuning · Dist… General AI Discourse filtered out ⌕ thread
Lewin Wanzer behold this box here... the internet! 🎁
AI Engineer | Anthropic Claude API & AW… General AI Discourse filtered out ⌕ thread
On-premise AI for critical infrastructure just got a lot more compelling. No cloud dependency, no latency, no data sovereignty risk. This is the hardware story that makes what we’re building at Utilyst inevitable. 💧
General AI Discourse filtered out ⌕ thread
This will make for a compelling addition with some of the work we're doing in the AI appliance space. Empowering organizations with meaningful AI workflows on-prem can lead to meaningful reduction in the majority of their cloud spend.
General AI Discourse filtered out ⌕ thread
How much it costs? In-house solution is for poor))) tell me how much it costs?
Sr Engineer General AI Discourse filtered out ⌕ thread
Thats 200B model on Q4 Quantisation not FP16
,, Not everything that can be counted c… General AI Discourse filtered out ⌕ thread
I need one of this OMG
Founder of @INVICTUS.AI | Computer Visi… General AI Discourse filtered out ⌕ thread
I'm not sure about how practical this mini PC would be to train any AI models, especially in terms of cooling during time-consuming AI model training processes. It might only survive as a thin client.
AI Specialist (ML) & Founder, Driving P… General AI Discourse filtered out ⌕ thread
Cuda is the problem
-- General AI Discourse filtered out ⌕ thread
Daniel Uhlemann my mac m1 ultra has similar specs. Might not be as fast but i had it for 5 years b
Private Secure Agentic AI Architect. Co… General AI Discourse filtered out ⌕ thread
Right things to say is it has probably enough ssd or memory to fit the model. That’s all. Nothing else about perf, tco can be claimed.
Starting something new. Stealth mode un… General AI Discourse filtered out ⌕ thread
The pace of AI hardware innovation is becoming extraordinary. Running large-scale models locally on a compact system would have seemed unrealistic just a few years ago. Developments like this could significantly expand access to advanced AI by reducing dependence on massive cloud infrastructure and centralized compute.
Director of Software Engineering General AI Discourse filtered out ⌕ thread
This could become a very important turning point for edge AI. As models become smaller, more efficient, and increasingly optimized for local hardware, AI may gradually move from massive centralized data centers toward personal devices and local inference systems. The long-term implications for privacy, latency, and AI accessibility could be enormous.
Co-founder of Vertex AI Labs | Former D… General AI Discourse relevant value: privacy + beneficence for: individual_users optimistic approval ⌕ thread → raw LLM
How does this compare to the NVIDIA DGX Spark ( and other GB10s ) and the Apple Mac Pro Ultra/Max ?
MBA, BE(Mech. Eng) Applied AI Practitio… General AI Discourse filtered out ⌕ thread
which run on the NVIDIA Graphics ? 😂
AI enthusiast skilled in Python, NLP & … General AI Discourse filtered out ⌕ thread
That’s what I need to use on Edge.
Developing state of art technologies fo… General AI Discourse filtered out ⌕ thread
Good AMD is back
Kazakh , Making world better General AI Discourse filtered out ⌕ thread
Future brains of ultra agile robotics systems
Assistant Manager General AI Discourse filtered out ⌕ thread
← Prev 1 2 Next →