After I complete my Local LLM series on @NVIDIAAI DGX Spark. Iw ill be writing 7 days of @GeminiApp! Are you excited? The Local LLM series has been doing good rounds on the internet! next is about the inference engines, LFG! I hope you like the animations ;)

Ws in the chat

This is your 3rd spark 😱 how much is that in your local? Here we can’t find it.

Did you try with multiple DGX Sparks yet? My frieng bought one and has been very disappointed of the performance, memory bandwidth throttles is to just being a small demo of DGX

3 can't be used for TP though... you want it for more concurrent sessions and more kv cache?

$ICARUS is live . CA : AxXHcoX6y1GhebHg5dHhgw82yFaLBJmhbb5qNEmkpump 2x NVIDIA DGX boxes linked up to run the newest Nemotron model locally. had to buy another :) @NVIDIAAI

Ohh my Bro is about to make his own data center 😆

yes - blog.kubesimplify.com/series…

Read the license

Congrats to the @MiniMax_AI team on the release of MiniMax M3, a long-context multimodal model for text, image, and video reasoning. 🙌 Try it today with our free GPU-accelerated endpoint on build.nvidia.com. Details: nvda.ws/4v4BWhD

@NVIDIAAI I'm developing a system to run local AI. I was wondering if I could get a DGX Spark to figure out the real concurrency you can obtain from that machine

Is there any place to learn this ?

Not bad

🔥🔥🔥🔥We up

I'm waiting for the amd Ryzen AI helo

Useful eval: compositional failure, not just FPS. When a requested behavior is missing or ambiguous, does the primitive refuse, recover, or choose a plausible wrong motion? For robotics, report contact-rich success under perturbation recovery latency.

also I just realized NVDA hosts free opensource models like k2.6 and m3 and glm5.1 low key waiting for k2.7 to drop in build.nvidia.com @NVIDIAAI