Tech2Wild

141 posts

Tech2Wild banner
Tech2Wild

Tech2Wild

@Tech2Wild

🎮 Tech, gaming, AI, and everything in between. 🤖 Building with it, not just talking about it. 🔥 From the mind of @ToNYD2WiLD

شامل ہوئے Mart 2026
59 فالونگ96 فالوورز
Tech2Wild
Tech2Wild@Tech2Wild·
Hmm wondering which is better: Gemma 4 12B or Qwen 3.6 35B-A3? 🤔
English
25
0
36
10.6K
Master Builder
Master Builder@MakerInParadise·
@Tech2Wild I can’t say anything negative about either model other than that 12B’s native vernacular is too informal for my liking… it has grok4.1/deepseek sentence structure and punctuation. Otherwise, I think that 12B is the better chat model and 35B the better reasoner/researcher.
English
2
0
3
1.2K
Tech2Wild
Tech2Wild@Tech2Wild·
@malikwas1f Good call I been running your recipes bro thanks for what you do
English
1
0
1
58
Tech2Wild
Tech2Wild@Tech2Wild·
Got the 3rd GPU setup (3x 3090s) but no TP=3, so I'm running a separate model or cloned 27B on the extra card. Been looking at Gemma 4 12B but honestly wondering if it's worth it when I can already run 27B or 35B at full context... What's your take? 🤔
English
6
0
5
839
Tech2Wild
Tech2Wild@Tech2Wild·
@sakurayukiai I have 35B running now. The issue I’m having is 2GPUs of 27B give me almost identical speeds as 1 GPU on 35B
English
2
0
0
1.3K
Sakura Yuki
Sakura Yuki@sakurayukiai·
@Tech2Wild If you can fit the 35B footprint, Qwen is wild. Only 3B active params means it runs circles around Gemma's 12B dense decode speeds, but Gemma 4 is way friendlier on a single consumer GPU.
English
3
0
9
1.4K
Tech2Wild
Tech2Wild@Tech2Wild·
@gospaceport Sir I literally just watched your video on your Quad Build from 9 months ago 🙏🏽. Debating whether you go to GEN 5 or just grab one of the motherboards you showed and stay Gen 4.
English
0
0
0
22
Tech2Wild
Tech2Wild@Tech2Wild·
TRIPLE 3090s…. Need a new MB and start building a RACK if I decide to go any further lol. Temporary rig for now I gotta get a rack 🤣🤣🤣
Tech2Wild tweet mediaTech2Wild tweet mediaTech2Wild tweet media
English
3
0
17
1.3K
Tech2Wild
Tech2Wild@Tech2Wild·
Now that I've learned so much about AI I've realized the amount of false info content creators put out.
English
0
0
0
62
Sakura Yuki
Sakura Yuki@sakurayukiai·
@Tech2Wild Q2 perplexity hit on a 550B is so brutal you're basically paying a massive latency and hardware tax to get the reasoning of a solid 70B. Wild engineering flex, but the math is pretty unforgiving.
English
1
0
2
233
Tech2Wild
Tech2Wild@Tech2Wild·
Ran NVIDIA Nemotron-3-Ultra-550B fully local across 2 DGX Sparks (188GB split via llama.cpp RPC) 🤯 Findings: it works + reasons — but ~5 tok/s, since RPC is round-trip-bound (dual-node is slower per-token than one; it's a capacity play). But I question bigger≠better: 2-bit 550B barely tops a clean 4-bit ~285B. Can we agree ?
Tech2Wild tweet media
English
4
1
18
2.3K
Tech2Wild
Tech2Wild@Tech2Wild·
@outsource_ Model: unsloth/NVIDIA-Nemotron-3-Ultra-550B-A55B-GGUF, UD-Q2_K_XL (~188 GiB, 6 shards)
Dansk
1
0
1
163
Captain HaHaa
Captain HaHaa@CaptainHaHaa·
Never underestimate the power of a mushroom monk Agile, well connected and wise. Another character in the upcoming short I'm calling "The Panpipe Adventurer"
English
50
36
410
32.6K
Tech2Wild ری ٹویٹ کیا
ToNYD2WiLD
ToNYD2WiLD@ToNYD2WiLD·
I honestly had this thought pop up in my head yesterday bro foreal. Like I’ve been diving heavy into AI and where that’s going and the efficiency and pricing of AI in China and how it’s winning people over. BUT now even our athletes like Step Curry. I am pro American but China has a plan and there way to it is to undercut American product.
Christina Faith@ChristinaFaith

@KariDaniels What folks don’t realize is China will be the number one economy in 5-10 years due to US negligence and the ramping up of MAGA economics

English
3
2
5
4K
Tech2Wild
Tech2Wild@Tech2Wild·
@AI_Homelab Yea I got one more left lol. After that I’m going to have to grab me a new motherboard and rig and begin my workstation lol
English
0
0
0
5
Simon
Simon@AI_Homelab·
@Tech2Wild Do you have enough available PCIe Lanes? (either supported on chip or by your CPU?)
English
1
0
0
25
Tech2Wild
Tech2Wild@Tech2Wild·
I just found out my motherboard has a slot for a 3rd GPU. What can 3 x RTX 3090s actually do? I need ideas, someone tell me please!
English
5
0
6
755
Tech2Wild
Tech2Wild@Tech2Wild·
Qwen, when?
English
0
0
0
22
Tech2Wild
Tech2Wild@Tech2Wild·
Going to bed now, @Alibaba_Qwen I am hoping to wake up to Qwen 35B A3 and/or 27B tomorrow.
English
0
0
2
95
Tech2Wild
Tech2Wild@Tech2Wild·
So this would do really well in a Reachy 2 Mini I'm thinking.
Ming-Yu Liu@liu_mingyu

Introducing NVIDIA Cosmos 3 We released NVIDIA Cosmos 3 last night. And today, seeing it take the top spots across 8+ open model leaderboards feels surreal. We spent months working towards this moment. Here’s the breakdown: The Leaderboard Wins World Reasoning 🏆 #1 open model on VANTAGE-Bench for vision AI 🏆 #1 overall on Traffic Anomaly Reasoning (TAR) World Generation 🏆 #1 open model on Artificial Analysis Image-to-Video leaderboard 🏆 #1 open model on Artificial Analysis Text-to-Image leaderboard 🏆 #1 open model on PAI-Bench for physical AI synthetic data generation 🏆 #1 open model on Physics-IQ, which measures accuracy on physical laws 🏆 #1 open model on R-Bench for world generation quality World Action 🏆 #1 on RoboArena for specialized policy 🏆 #1 on RoboLab for action generation But the leaderboards are only part of the story. The real story is why we built Cosmos 3 in the first place. The Problem Training robots and autonomous systems in the real world is painfully hard. Robots need to try the same thing numerous times before they succeed reliably. Self-driving cars need rare edge cases that may never happen naturally. Smart machines need to understand physics, motion, contact, failure, and surprise. And real-world data is slow, expensive, and sometimes dangerous to collect. At some point, the answer cannot just be “collect more data.” You can’t collect your way out of an infinite physical world. You have to generate it. That… was the question behind Cosmos: Can one model understand the physical world deeply enough to reason about it, simulate it, and generate actions inside it? What We Built Cosmos 3 is the first omni-model for physical AI. It can understand and generate across: language · images · video · audio · action sequences It is not just a VLM. Not just a video generator. Not just a robot policy model. It is all of them, in one single model. That matters because physical AI has been fragmented for a long time. Cosmos 3 is our attempt to collapse that fragmentation. Depending on how you configure the inputs and outputs, the same model can act as a vision-language model, a video/world generator, a world simulator, or a world-action model. No separate architecture required. The Architecture Under the hood, Cosmos 3 uses a dual-tower Mixture-of-Transformers architecture. One tower is autoregressive for reasoning. It handles next-token prediction for language and discrete understanding. The other tower is diffusion-based- for generation. It denoises images, video, audio, and action trajectories. Two towers. Dual-stream joint attention. One shared world representation. Each modality gets its own tools: visual encoders, video VAEs, audio VAEs, and action projectors that can map different embodiments into a unified action space. Action is a first-class modality in Cosmos 3. That’s what makes it more than a video model. It doesn’t just predict and generate what the world might look like. It can connect reasoning and world modeling to physically grounded action. Why This Matters One of the most interesting findings from the ablation work is that training action domains together creates positive transfer. That means adding more embodiments does not just add more use cases. It can actually make the model better. This is the heart of why omnimodal training matters. A shared world representation is not just convenient. It can make each individual task stronger. That’s the part that feels like the beginning of something much bigger. The part I’m most excited about is that Cosmos 3 is fully open. Developers get the models, scripts, optimization, inference endpoints, post-training recipes, datasets, and benchmarks. Everything is available under the Linux Foundation’s OpenMDW 1.1 License. You can use Cosmos 3 out of the box. You can use the VLM, world model, or world-action pieces separately. You can post-train it for your own domain, embodiment, or accuracy target. That’s what makes this feel different. Cosmos 3 is not just a model release. It is the foundation for building intelligence for autonomous machines. For me, Cosmos 3 feels like a step toward a world where physical AI development becomes much more scalable and accessible - to a new age of developers and agents. That’s what we built Cosmos 3 for. I cannot wait to see what you build with it. Download Models on Hugging Face huggingface.co/collections/nv… Customize Models on GitHub github.com/NVIDIA/cosmos Read the Tech Blog to Learn More developer.nvidia.com/blog/develop-p…

English
0
0
0
66