News Nvidia counters AMD DeepSeek benchmarks, claims RTX 4090 is nearly 50% faster than 7900 XTX

Page 3 - Seeking answers? Join the Tom's Hardware community: where nearly two million members share solutions and discuss the latest tech.
You mean Nvidia didn't run their tests well and used the weight of their hooting fanboy army to call it an own.

Nvidia benchamaks their cards with CUDA and Vulkan with the AMD cards and declares victory

Imagine if the AMD benchmarks had used Vulkan for the Nvidia cards and ROCm for the AMD cards?

people would be crying blue murder
I'd argue whoever won ran their testing the best.
 
Yup... seems like independent benchmarks are going to be veeery needed.

Interestingly enough, I'd say that Strix Halo will probably trounce 5090 and 7900 on large models thanks to the GPU having access to huge 128 GB of fairly speedy memory (Quad-channel LPDDR5x-8000). Maybe even the integrated NPU could give it an additional bump.
For a ton more money? Lol.
 
The irony of your rebuttal there is Deepseek made a huge fuss about it costing far less to train the model. So cost was immediately made a significant metric. You can buy 2 XTXs for less than the cost of a 4090.
But things don't scale so easily just because you put two together. Lol.
 
But things don't scale so easily just because you put two together. Lol.
there isn't much of a speed increase with tok/sec when you go with 2 gpu's most people do it for the additional VRAM capacity.

i've seen results from 2x3090 rigs and 2x4090's and the purpose of the second gpu was to run 70B models very little speedup performance wise.

For a ton more money? Lol.
it will cost less than the MSRP for a 5090 and you will be able to run much larger models.
 
there isn't much of a speed increase with tok/sec when you go with 2 gpu's most people do it for the additional VRAM capacity.

i've seen results from 2x3090 rigs and 2x4090's and the purpose of the second gpu was to run 70B models very little speedup performance wise.


it will cost less than the MSRP for a 5090 and you will be able to run much larger models.

The flip side is you can get larger models to run without having the VRAM, but there is a performance hit.