NVIDIA DGX Spark vs RTX 4090 | LLM inference, training speed and more

Bystaff



This video compares the NVIDIA DGX Spark and NVIDIA RTX 4090 across several benchmarks and attributes such as price and footprint.

Benchmark code – https://github.com/mrdbourke/gpu-benchmarking
Exolabs blog post – https://blog.exolabs.net/nvidia-dgx-spark/
DGX Spark – https://nvda.ws/4iQXZU4
Deep learning PC specs – https://pcpartpicker.com/user/mrdbourke/saved/#view=sJCnGX

Courses I teach:
Learn AI/ML (beginner-friendly course) – https://dbourke.link/ZTMMLcourse
Learn Hugging Face – https://dbourke.link/ZTMHuggingFace
Learn TensorFlow – https://dbourke.link/ZTMTFcourse
Learn PyTorch – https://dbourke.link/ZTMPyTorch

Connect elsewhere:
Download Nutrify (my startup) – https://apple.co/4ahM7Wc
My website – https://www.mrdbourke.com
X/Twitter – https://www.twitter.com/mrdbourke
LinkedIn – https://www.linkedin.com/in/mrdbourke
Get email updates on my work – https://dbourke.link/newsletter
Read my novel Charlie Walks – https://www.charliewalks.com

Timestamps:
0:50 – RTX 4090 vs DGX Spark Specs
1:57 – Quick Summary (note: spoilers)
2:39 – Footprint and Size
4:02 – Benchmarks Overview
4:43 – Results
4:48 – vLLM Input and Output Speed
5:06 – llama.cpp Input and Output Speed
6:32 – Image Generation Results
7:08 – LLM Fine-tuning
8:42 – Object Detection Model Fine-tuning
9:11 – What should you get?

source

Similar Posts