Amine

@MiaAI_lab @NVIDIAAI im kind of restarted, could you provide a parts list for the best optimized single rtx pro 6000 build for inference pretty please!

@themodev @NVIDIAAI it's the same as single dgx spark

What are the best models you can run on your @NVIDIAAI DGX Spark? ✨ Mid-July 2026 Edition 1× DGX Spark • ⁠Qwen 3.6 35b NVFP4 — 256k ctx, 81 tok/s • ⁠Qwen 3.6 27b NVFP4 — 256k ctx, 33 tok/s 2× DGX Sparks ← sweet spot! • DeepSeek v4 Flash — 1M ctx, 60 tok/s • MiMo-V2.5 — 1M ctx, Full Omni, 31 tok/s • Step-3.7-Flash — 256K ctx, 30 tok/s 3× DGX Sparks With three units, I recommend running a large model across two of them and a smaller one on the third. I'd personally run DeepSeek v4 Flash + Qwen 3.6 35B. This setup gives you DeepSeek v4 Flash speeds for coding, plus strong agentic workflows and image support from Qwen 3.6 35B. 4× DGX Sparks GLM 5.2 NVFP4 across all 4 units — if you have four units, this is the one to run! Links and repos below 👇

Rest assured that GPT 5.6 Sol will stay in the ChatGPT subscription you pay for. Including Go, Plus and Pro subscriptions. At least until we ship an even better model.

And Pi out of the box sends less than 1.2k tokens ;) systima.ai/blog/claude-co…

@0xSero for max inference ofc

@0xSero can you send me a single rtx 6000 pro build parts list

Yes sir, I’m sure I want to sell my second kidney for another RTX Pro 6000

@bekacru @koomen congrats @bekacru

Better Auth is joining Vercel! From the very beginning, this team has been my biggest inspiration and has always reflected many of the reasons I started working on Better Auth. I’m incredibly grateful to our community, our team, our investors - in particular @koomen and @arnavsahu341 from @peakxvpartners for believing in my vision and taking a chance on me. And thank you everyone @vercel that made this happen - I'm excited to to be building together!! I’ve shared some thoughts on the blog post linked Excited for what’s ahead ❤️ better-auth.com/blog/better-au…

how long after sex is it appropriate to open claude?

Based on strong positive feedback from customers in our beta test program, @SpaceXAI will make Grok 4.5 available to the public tomorrow. It is an Opus-class model, but faster, more token-efficient and lower cost.

Listen up. Livestream at 10am.

What's the craziest thing you've seen on LinkedIn..?

I have officially moved the majority of my dev work over to Linux. I couldn't be happier. Here's a video about how and why I made the move.

It's been 18 days since Fable 5 was banned. Kind of insane. I genuinely thought it would be back after a few days.

Why would I pay more for less?

The world changed this week Governments started banning frontier models. Hardware has become unobtainable The single most important thing you can be doing right now is getting into local AI In this video I cover EVERYTHING local AI. Most important video you'll watch this week:

sleep?

We must build our own, open-source, decentralized, distributed AGI there is no other way. right now politicians and big tech executives are holding us hostage they literally hold our future in their hands this HAS to change.

I'm afraid we've entered a dark era in AI model development and access.