RTX Spark looks like a Windows mistake, but NVIDIA may be playing a much bigger game. Try out ChatLLM - http://chatllm.abacus.ai/ltf and Abacus AI DeepAgent - http://deepagent.abacus.ai/ltf 🛒 Gear Links 🛒 👀 2 400Gbps switch: https://bhpho.to/4r9vJi1 👀👀 4 400Gbps switch: https://bhpho.to/4qQqOlI 👀 MSI EdgeExpert now available here: https://amzn.to/40luUHG 👀 ASUS GX10: https://amzn.to/4kROLb8 👀 DGX Spark on SALE: https://amzn.to/4kOnczp 🪛🪛Highly rated precision driver kit: https://amzn.to/4fkMVfg 💻☕ Favorite 15" display with magnet: https://amzn.to/3zD1DhQ 🎧⚡ Great 40Gbps T4 enclosure: https://amzn.to/3JNwBGW 🛠️🚀 My nvme ssd: https://amzn.to/3YLEySo 📦🎮 My gear: https://www.amazon.com/shop/alexziskind 🎥 Related Videos 🎥 🧳🧰 Mini PC portable setup - https://youtu.be/4RYmsrarOSw 🍎💻 Dev setup on Mac - https://youtu.be/KiKUN4i1SeU 💸🧠 Cheap mini runs a 70B LLM 🤯 - https://youtu.be/xyKEQjUzfAk 🧪🔥 RAM torture test on Mac - https://youtu.be/l3zIwPgan7M 🍏⚡ FREE Local LLMs on Apple Silicon | FAST! - https://youtu.be/bp2eev21Qfo 🧠📉 REALITY vs Apple’s Memory Claims | vs RTX4090m - https://youtu.be/fdvzQAWXU7A 🧬🐍 Set up Conda - https://youtu.be/2Acht_5_HTo ⚡💥 Thunderbolt 5 BREAKS Apple’s Upcharge - https://youtu.be/nHqrvxcRc7o 🧠🚀 INSANE Machine Learning on Neural Engine - https://youtu.be/Y2FOUg_jo7k 🧱🖥️ Mac Mini Cluster - https://youtu.be/GBR6pHZ68Ho * 🛠️ Developer productivity Playlist - https://www.youtube.com/playlist?list=PLPwbI_iIX3aQCRdFGM7j4TY_7STfv2aXX 🔗 AI for Coding Playlist: 📚 - https://www.youtube.com/playlist?list=PLPwbI_iIX3aSlUmRtYPfbQHt4n0YaX0qw — — — — — — — — — ❤️ SUBSCRIBE TO MY YOUTUBE CHANNEL 📺 Click here to subscribe: https://www.youtube.com/@AZisk?sub_confirmation=1 — — — — — — — — — Join this channel to get access to perks: https://www.youtube.com/channel/UCajiMK_CY9icRhLepS8_3ug/join — — — — — — — — — 📱 ALEX on X: https://x.com/digitalix #rtxspark #gdxspark #llm
ADVERTISEMENT
> "a new era of PC" > looks inside > a laptop
Nvidia cleaning out the parts bin of leftover spark chips.
More, it needs 256GB of memory so that you have 128GB for LLMs and 128GB for development.
NVIDIA - "We teamed up with Microsoft to sell a LOT of AMD Strix Halo!"
So it’s a dgx spark with different memory skus
The tomato, man that got me…..
It runs a sloperating system I heard.
And for the low LOW price of $4,999.99!
me watching this while looking for 15yo Thinkpad deals...
The thing that irritates me is that the GB10 what kind of underwhelming when it came out a year ago. Now it's just not very impressive.
You're one of my favorite tech people to follow around here. Truly impartial, but not bootlicking anyone. Really honest about where your general daily driver/prefered dev environment is, at the same time not dismissing whatever else interesting appears in the landscape. Keep up the great job.
I wonder how well this might integrate with Windows Subsystem for Linux
0:53 should have 100% been the video thumbnail
Hey Alex, if one day you can create a short video on how to use Abacus AI that you usually have as sponsors or as ad, it would be great. Thanks
4:30 That normal people can buy?! The cheapest option will be probably around 2000USD and then go up to 6-7000USD. And, as you said, it is at the level of AMD Strix Halo 395 chip that is already out, in both laptop and mini PC form and can already run both Linux and Windows.
Battery test with local LLM on the RTX Spark laptop please!
Very good video. You've highlighted several problems with the very essence of this machine. An ARM CPU, okay, and CUDA. The ARM core will be energy-efficient, but the CUDA cores will be much more power-hungry and will consume as much energy as the DGX cores, which are much better ventilated. That much heat in a laptop case, especially a thin one, will make it difficult to use, if not impossible, and risks shortening the PC's lifespan. Another point: the 128GB of RAM to be able to play with high-end models. DDR5 won't be any cheaper; the machine will have a stratospheric price. In the end, the fact that it boots into Windows and not Linux becomes a minor detail.
I love this channel for one absolute reason it's takes complex topics and makes it so simple for the average person to understand like a proffesional
NVidia drivers are still nightmare to install on Linux.
It's just Apple silicone for Windows