Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Asus Ascent GX10

asus.com

Post reply on HN
Print view View original

181–190 of 203 posts

Re: Asus Ascent GX10

#181

Post by bigyabai »

tuna74 wrote: post #164
bigyabai wrote: post #110

Earlier quoted context omitted.

Would almost be a no-brainer if the Mac GPU wasn't a walled garden.

Is that any different from nVidia?

Yes? Apple does not document their GPUs or provide any avenue for low-level API design. They cut ties with Khronos, refuse to implement open GPU standards and deliberately funnel developers into a proprietary and non-portable raster API.

Nvidia cooperates with Khronos, implements open-source and proprietary APIs simultaneously, documents their GPU hardware, and directly supports community reverse-engineering projects like nouveau and NOVA with their salaried engineers.

Pretty much the only proprietary part is CUDA, and Nvidia emphatically supports the CUDA alternatives. Apple doesn't even let you run them.

Re: Asus Ascent GX10

#182

Post by wtallis »

hasperdi wrote: post #147
WhitneyLand wrote: post #46

GX10 vs MacBook Pro M4 Max: - Price: $3k / $5k - Memory: same (128GB) - Memory bandwidth: ~273GB/s / 546GB/sec - SSD: same (1 TB) - GPU advantage: ~5x-10x depending on memory bottleneck - Network: same 10Gbe (via TB) - Direct cluster: 200Gb / 80Gb - Portable: No / Yes - Free Mac included: No / Yes - Free monitor: No / Yes - Linux out of the box: Yes / No - CUDA Dev environment: Yes : No

AMD 395+ is more bang for the buck IMO. GMKtec EVO-X2 vs GX10 vs MacBook Pro M4 Max Price: $2,199.99 / $3,000 / $5,000 CPU: Ryzen AI Max 395+ (Strix Halo, 16C/32T) / NVIDIA Grace Blackwell GB200 Superchip (20-core ARM v9.2) / Apple M4 Max (12C) GPU: Radeon 890M (RDNA3 iGPU) / Integrated Blackwell GPU (up to 1 PFLOP FP4) / 40-core integrated GPU Memory: 128GB LPDDR5X / 128GB LPDDR5X unified / 128GB unified Memory band…

The DGX Spark, Ascent GX10, and related machines have no relation to NVIDIA Grace Blackwell GB200. The chip they are based on is called GB10, and is architecturally very different from NVIDIA's datacenter solutions, in addition to being vastly smaller and less powerful. They don't have anything resembling the Grace CPU NVIDIA used in Grace Hopper and Grace Blackwell datacenter products. The CPU portion of GB10 is a Mediatek phone chip's CPU complex that metastasized, not NVIDIA's datacenter CPU cut down.

Re: Asus Ascent GX10

#183

Post by fodkodrasz »

7734128 wrote: post #14

If you touch the image when scrolling on mobile then it opens when you lift your finger. Then when you press the cross in the corner to close the image, the search button behind it is activated. How can a serious company not notice these glaring issues in their websites?

Wait until you start using an ASUS computer, and hit the BIOS/UEFI issues...

I learned the hard way that ASUS translates do "don't buy ever again".

Re: Asus Ascent GX10

#185

Post by bayindirh »

janstice wrote: post #153
bayindirh wrote: post #136

Earlier quoted context omitted.

NVIDIA H200 idles at 75 watts. I'm not keeping my hopes high on that, either.

To be fair, if I paid $30k+ for an H200, I’d want it to be making money 24/7 rather than idling, so the idle power draw would be strictly theoretical.

It's not always about money.

Re: Asus Ascent GX10

#186

Post by tgma »

wtallis wrote: post #182
hasperdi wrote: post #147

Earlier quoted context omitted.

AMD 395+ is more bang for the buck IMO. GMKtec EVO-X2 vs GX10 vs MacBook Pro M4 Max Price: $2,199.99 / $3,000 / $5,000 CPU: Ryzen AI Max 395+ (Strix Halo, 16C/32T) / NVIDIA Grace Blackwell GB200 Superchip (20-core ARM v9.2) / Apple M4 Max (12C) GPU: Radeon 890M (RDNA3 iGPU) / Integrated Blackwell GPU (up to 1 PFLOP FP4) / 40-core integrated GPU Memory: 128GB LPDDR5X / 128GB LPDDR5X unified / 128GB unified Memory band…

The DGX Spark, Ascent GX10, and related machines have no relation to NVIDIA Grace Blackwell GB200. The chip they are based on is called GB10, and is architecturally very different from NVIDIA's datacenter solutions, in addition to being vastly smaller and less powerful. They don't have anything resembling the Grace CPU NVIDIA used in Grace Hopper and Grace Blackwell datacenter products. The CPU portion of GB10 is a M…

Where does MediaTek come into the picture? Don't they take some ARM Cortex IP directly from ARM just like MediaTek and many others?

Re: Asus Ascent GX10

#187

Post by whywhywhywhy »

MangoToupe wrote: post #93
whywhywhywhy wrote: post #71

Earlier quoted context omitted.

Better support than MPS and nothing Apple is shipping today can compete with even the high end consumer CUDA devices in actual speed.

Presumably the second point is irrelevant if you're choosing among devices with unified memory.

Depends if you care how fast the result arrives. Imagery gen is a very different tool at <12 seconds an image vs nearer to 1 minute.

Re: Asus Ascent GX10

#189

Post by embedding-shape »

woodson wrote: post #92
bigyabai wrote: post #67

Earlier quoted context omitted.

Somehow, it is still cheaper to own 10x RTX 3060s than it is to buy a 120gb Mac.

The Mac will be much smaller and use less power, though.

How does the introspection/debugging tools look like for Apple/Mac hardware when it comes to GPU programming?

Re: Asus Ascent GX10

#190

Post by embedding-shape »

kennethallen wrote: post #176
stogot wrote: post #175

Earlier quoted context omitted.

Noob here. Why is that number bad?

Running LLMs will be slow and training them is basically out of the question. You can get a Framework Desktop with similar bandwidth for less than a third of the price of this thing (though that isn't NVIDIA).

> Running LLMs will be slow and training them is basically out of the question

I think it's the reverse, the use case for these boxes are basically training and fine-tuning, not inference.

Post reply on HN