BlackwellBoy

Sovereign local AI architect • 824 GB heterogeneous beast (RTX 5090 + 5×3090 + 5× DGX Spark + M4 Mac Mini) Hermes ftw.

[BlackwellBoy @Blackwellboy]

Drop your GPU below and I’ll tell you exactly what model and config to run on it.

JOKES. No need.

Qwen 3.6 27b @UnslothAI . All day. All night.

[BlackwellBoy @Blackwellboy]

the cloud taught a generation to rent intelligence by the sip. then the price went up. then the limits tightened.
the ppl who saw it coming were already running their own machines and never noticed.

[BlackwellBoy @Blackwellboy]

@danielbitpro @MiaAI_lab @Tech2Wild also love that you got the asus one, they are so nice

[BlackwellBoy @Blackwellboy]

@danielbitpro @MiaAI_lab @Tech2Wild hahahaha thats great to hear ! I hope you enjoy it !

[BlackwellBoy @Blackwellboy]

@danielbitpro @MiaAI_lab @Tech2Wild no chance, give it a whirl ! haha

[BlackwellBoy @Blackwellboy]

@danielbitpro @MiaAI_lab @Tech2Wild go straight to 32 see what you get ;)

[BlackwellBoy @Blackwellboy]

@Blackwellboy @MiaAI_lab @Tech2Wild Already up and running, @MiaAI_lab put the recipe up for the Qwen3.6 35b as if she knew the package was on its way!

[BlackwellBoy @Blackwellboy]

@MichaelGannotti @NVIDIAAI always here to help you mike ! :D you legend

[BlackwellBoy @Blackwellboy]

Every man reaches a point where the cluster wants to grow but the wife says no. That's where I come in. I build the case, cite the ROI, reference the tax writeoff, land the plane. Head of the Spark Justification Committee. Wives fear me. DMs open. @NVIDIAAI

[BlackwellBoy @Blackwellboy]

@advancedjd @NVIDIAAI that is so dodgey, sorry to hear man

[BlackwellBoy @Blackwellboy]

Everyone dl'ing Qwen + GLM like the tap stays on forever. the tap has a country attached to it.
reminder "open weights" is a policy decision, not a law of physics, and policies change in a single meeting. Every model on your drive jst got more valuable & a lot less replaceable.

[Jukan @ ICML @jukan05]

CHINA CONSIDERS RESTRICTING OVERSEAS ACCESS TO CUTTING-EDGE AI MODELS

China’s Ministry of Commerce has led meetings over the past month with major AI companies, including Alibaba, ByteDance, and https://t.co/YDe0KRldDB, to discuss measures that would restrict overseas access to cutting-edge AI models, including models that have not yet been released.

The discussions reportedly include not only closed-source models but also open-weight models. However, the scope of application is still under debate, and the rules may ultimately apply only to future frontier models.

Officials have also discussed designating the leakage or theft of proprietary AI technologies as a national security crime, with stronger penalties, as well as restricting the types of foreign capital that can invest in Chinese AI startups.

The backdrop is the U.S. move to strengthen export controls on AI models, along with national security concerns over cutting-edge models that could possess advanced cyberattack capabilities.

Chinese authorities are reportedly concerned that advanced U.S. cybersecurity AI models could be used to exploit vulnerabilities in Chinese software.

Since the beginning of this year, China has continued to tighten measures to prevent AI technology from being transferred overseas. Authorities have investigated whether Chinese AI startups that relocated abroad violated export control laws, while also strengthening oversight of overseas transactions involving Chinese investors, technology, data, and national security concerns.

Future regulations could take the form of a tiered framework based on technological capability. Basic open-source AI models may be managed through a filing system, high-performance models may be subject to security reviews, and the most sensitive frontier models may be banned from public release or restricted to use within China.

[BlackwellBoy @Blackwellboy]

@advancedjd @NVIDIAAI oh shit, no way...

[BlackwellBoy @Blackwellboy]

@danielbitpro AYEEE WELCOME TO THE FAM! make sure you check out @MiaAI_lab and @Tech2Wild builds and containers :D

[BlackwellBoy @Blackwellboy]

@lucastech i love all these options that are showing up and everyones own preferences !

[BlackwellBoy @Blackwellboy]

Everyone out here flexing tmux and ssh configs and I’m sitting in a cafe RustDesk’d into my home pc. 3 monitors, the whole rig, streamed to a Mac. Why terminal into a machine when I can just remote into the entire machine. Not sure if genius or newb. Anyone else or just me.😅

[BlackwellBoy @Blackwellboy]

@koretexai @NVIDIAAI at your service my friend !

[BlackwellBoy @Blackwellboy]

@ExileAI_0 @NVIDIAAI very true 😅

[BlackwellBoy @Blackwellboy]

@ChicouTiMix @NVIDIAAI damn, ive paid for all 7 of mine so far , i havent ever gotten so much as a free SSD haha

[BlackwellBoy @Blackwellboy]

@thatcofffeeguy @gabu3d_pl @mr_r0b0t i suggest a small wait :D think they will get a lot better

[BlackwellBoy @Blackwellboy]

@thatcofffeeguy @NVIDIAAI you will tell your wife and you will join XD

[BlackwellBoy @Blackwellboy]

@georgecursor @NVIDIAAI thats the spirit

[BlackwellBoy @Blackwellboy]

@SOntheotherside 3B , thats pretty solid effort i wonder what im doing havent checked of late

[BlackwellBoy @Blackwellboy]

@0xSero Ooooh do it do it!
I love to watch builds !

[BlackwellBoy @Blackwellboy]

@ChicouTiMix @MiaAI_lab how much was the price back then?are they going up over there?

[BlackwellBoy @Blackwellboy]

Most people can’t run models this big smoothly. Mia fixes that 🔥

Tencent Hy3-295B on 2x DGX Spark.

295B parameters. 128k context. MTP.
Dead simple setup.

~20 tok/s single session. ~58 in 6 concurrent.

It feels solid. Really solid.
See for yourself 👇 @MiaAI_lab

[Mia @MiaAI_lab]

Run Tencent Hy3-295B on 2x @NVIDIAAI DGX Spark with EASE🔥

128k context • MTP • Up to 6 concurrent sessions

Performance:
~20 tok/s in single session
~58 tok/s in 6 concurrent sessions (cumulative)

First impressions: the model feels very solid. More benchmarks and real-world tests coming soon!

Big thanks to the DGX community for the original work.

Get it here 👇

https://t.co/H15D1zvZPv