This Chinese developer linked two $2,999 NVIDIA DGX Sparks into one box and runs the full Qwen3-235B…
@browomo23K followers
94,424 views
22 Comments
Comments from the original post on X (Twitter)

@ruider92545
Yeah, it is 1500s permutation of the same BS. A Chinese developer, Malaysian teacher, Japanese influencer...🤣🤣🤣 I do the same without a fancy super duper shiny whatever specialised developer equipment.
11 likes

@browomo
Wow how powerful is this infrastructure?

@ruider92545
Good compute power 💪, 3-20 TOK/s 😂, les then 300W under the heavy load 💪, no air-con for cooling 💪, 400B+ FP16/BF16 local LLM models 💪, powered by solar panels💪. 5💪: 1😂 = 😇
2 likes

@browomo
Ahhahahahah Bro this is already a whole farm
1 like

@digitalnoah
I’m pro AI and a local AI enthusiast. There’s three things you’re misrepresenting here. 1. Qwen 3-235B isn’t a very good model compared to Chat GPT 5.5, Opus 4.8, or even Composer 2.5 Local AI is valuable, but doesn’t replace frontier models, it supplements them for easier tasks. 2. When you string 2 computers together, it doesn’t create a single memory pool. Some software lets you split the jobs, as you stated here, but it’s sub optimal at best. 3. DGX spark boxes are slow. Very slow. Under 300 GB/s memory bandwidth means you’re running weaker models and you’re getting slower tok/s. There’s so many incredible things you can do with local, sovereign AI, but you have to set your expectations right. The hardware is expensive. The models are waaaay dumber than frontier. The tok/s speed is dependent on memory bandwidth and most home builds are slow as molasses.
9 likes

@MEZ_tech
Crazy thing is even with this setup, not sure the electricity costs are less than the token costs for the equivalent token usage, not to mention this setup isnt even capable of producing high token throughput when desired. Absolutely love the idea of local llms, especially wrt data privacy, but theyre not necessarily cost effective
1 like

@browomo
I see it differently. Two of these boxes draw just 120W combined that's pennies for electricity compared to a $2,000 monthly cloud bill. And 10 tokens a second is more than enough to comfortably read the response in real time.
1 like

@MEZ_tech
86400 seconds/day * 10 tok/s = 864000 tok/day max output (disregard encoding time, etc). Qwen 3 255B output token costs are $0.45/1M So, cloud costs would be roughly $0.45/day = $13.5/mo if using Qwen 3 255B at the equivalent level of usage (rounding up tok/day to 1M to account for input tokens). So no, it does not "save $2000/mo"
1 like

@browomo
wow that's a powerful argument

@asukahaox
それはすごいですね!技術の進歩は本当に驚くべきです。将来的にAIに支払い続ける必要がない方法を考えると、この方法はとてもクリーンで効果的ですね。

@Quake_jr
Data centres gotta re-diversify major purposes cx DGX fixed consumer cloud services…..Oooppssss

@Christi18676713
@IdleProtocol $Idle

@0xGrebe
bro turned a cloud bill into a desk appliance lol

@Chexxee
bro really turned $2k a month into a desk appliance lol

@kanukagi
それは本当に革命的ですね!自宅でAIを稼働させる方法が素晴らしいです。

@FarAICoder
curious if the cable is just ethernet or something custom for that 10 tokens/sec speed what happens if one spark dies mid-request

@caliroi70
Et comment puise-t-il l’information en live sur le net pour préparer ses réponse ?

@kevinchappell
You should tell your model to be less wordy when writing posts. It's just writing the same thing 3 different ways.

@regsky_
yeah didnt we all try this day one of dgx spark? what changed, or are yall running at low tps?

@UselessTreasure
So I think the point of this, is that you don't now what youre doing. Am interpreting that right?

