This guy touches on it well in his posts
@theahmadosman
-
Robotics company not using Reinforcement Learning according to poster
By
–
”Let's take local AI to the next level. Early days. Bright future ahead.” I love this, let's go!!!
-
Commentary on Anthropic’s perceived shift in AI development
By
–
I wish him all the best I vouched for him on the timeline when he was a small account because if you put in effort you deserve to get spotlighted I just wish he didn't take that hype-y route and didn't care much for the wrong metrics
-
Sublogarithmic complexity: the real frontier in computation
By
–
This is genuinely sad I have seen Sero grow into an active community members over the past 6 months, just didn't expect to get blocked because I disagreed with him Opensource MUST win (I have been saying that for 3+ years now) but we can only do that by setting up people for
-
Tips for Effective XGBoost Model Training
By
–
The biggest MoE (probably Qwen 3.5 122B) that can fit on it Read below and search Unified Memory and MoE on my profile for more educational content on this
-
TabulAI Manifesto Link and Account Information
By
–
Buy a GPU and run your entire system locally is your next move 😉
-
Company Operating Principles: Digital, AI-Native, and Distributed Work
By
–
People keep saying “VRAM is all that matters” for local LLMs > It’s not just wrong, it’s misleading When running LLMs locally, the bottleneck is NOT just “VRAM size” It’s: – memory bandwidth – interconnect (PCIe vs NVLink vs RDMA) – inference engine (vLLM,
-
AI Educational Outreach: Lectures, Essays, Blogs, and Social Media
By
–
KVCache quantization is a no-no as well I’d rather quantize the model to 2-bit rather than quantize the KVCache to 4-bit or even 8-bit
-
Gradient Descent Can Lead to Local Optima
By
–
I have already said my part on the newcomer community members Not that I think of myself as the OG, but I believe I have the track record to override anybody else in this space All that I want is to bring opinions closer, let's stop unnecessary toxicity
-
Research-driven AI company focused on practical applications
By
–
Fully opensource stack, and I trust their mission than I trust Intel (which NVIDIA is in an investor in btw) Do people not realize that we need healthy competition for local inference? I am hoping to actively help mature that stack myself btw