Asus Ascent GX10 • Hacker News Board

Re: Asus Ascent GX10

#151

Post by dang » Mon, Nov 10, 2025, 8:17 PM UTC

wmf wrote: post #91

dang wrote: post #88

One past related thread. Any others? The Asus Ascent GX10 a Nvidia GB10 Mini PC with 128GB of Memory and 200GbE - https://news.ycombinator.com/item?id=43425935 - March 2025 (50 comments) Edit: added via wmf's comment below: "DGX Spark has only half the advertised performance" - https://news.ycombinator.com/item?id=45739844 - Oct 2025 (24 comments) Nvidia DGX Spark: When benchmark numbers meet production reality - htt…

It's the same as DGX Spark so there are several: https://news.ycombinator.com/item?id=45586776 https://news.ycombinator.com/item?id=45008434 https://news.ycombinator.com/item?id=45713835 https://news.ycombinator.com/item?id=45575127 https://news.ycombinator.com/item?id=45611912 https://news.ycombinator.com/item?id=43409281 https://news.ycombinator.com/item?id=45739844

Thanks! Added above.

Re: Asus Ascent GX10

#152

Post by janlukacs » Mon, Nov 10, 2025, 8:22 PM UTC

the_real_cher wrote: post #52

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?

Enshittification. Its not that they dont notice. They dont care.

but it has AI in it.

Re: Asus Ascent GX10

#153

Post by janstice » Mon, Nov 10, 2025, 8:39 PM UTC

bayindirh wrote: post #136

qwertox wrote: post #135

Earlier quoted context omitted.

I wouldn't mind if it burns 200 watts while it does the task, as long as it idles at below 30W

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.

Re: Asus Ascent GX10

#154

Post by bigyabai » Mon, Nov 10, 2025, 8:42 PM UTC

MangoToupe wrote: post #142

bigyabai wrote: post #114

Earlier quoted context omitted.

It is not. Unified memory is not a panacea, it says nothing about the compute performance of the hardware. The Spark's GPU gets ~4x the FP16 compute performance of an M3 Ultra GPU on less than half the Mac Studio's total TDP.

right, but that doesn't describe a "high end consumer CUDA device". Nothing under that description has unified memory.

Every CUDA-compatible GPU has had support for unified memory since 2014: https://developer.nvidia.com/blog/unified-memory-cuda-beginn...

Can you be a bit more specific what technology you're actually referring to? "Unified memory" is just a marketing term, you could mean unified address space, dual-use memory controllers, SOC integration or Northbridge coprocessors. All are technologies that Nvidia has shipped in consumer products at one point or another, though (Nintendo Switch, Tegra Infotainment, 200X MacBook to name a few).

Re: Asus Ascent GX10

#155

Post by bigyabai » Mon, Nov 10, 2025, 8:42 PM UTC

wmf wrote: post #121

lend000 wrote: post #98

Is there something similar with twice the memory/bandwidth? That's a use case that I would seriously consider to run any frontier open source model locally, at usable speed. 128GB is almost enough.

Mac Studio

Even an M3 Ultra won't put up similar GPU compute to a DGX Spark: https://blog.exolabs.net/nvidia-dgx-spark/

Fill up the memory with a large model, and most of your memory bandwidth will be waiting on compute shaders. Seems like a waste of $5,000 but you do you.

Re: Asus Ascent GX10

#156

Post by guerrilla » Mon, Nov 10, 2025, 8:53 PM UTC

darkwater wrote: post #104

guerrilla wrote: post #97

Earlier quoted context omitted.

It doesn't give a good idea of anything. We already know it has 128GB unified memory from the first bullet point on the page.

GP was subtly implying that the text was written by an LLM (running in the very same Ascent GX10).

Ah! Thanks for explaining. haha

Re: Asus Ascent GX10

#157

Post by cmxch » Mon, Nov 10, 2025, 9:04 PM UTC

maxbaines wrote: post #3

Looks like a pretty useful offering, 128Gb Memory Unified, with the ability to be chained. IN the Uk release price looks to be £2999.99 Nice to see AI Inference becoming available to us all, rather than using a GPU ..3090etc. https://www.scan.co.uk/products/asus-ascent-gx10-desktop-ai-...

At that price (roughly 4000 USD), one could build a full HBM powered Xeon system from the Sapphire Rapids generation.

Either build a single socket system and give it some DDR5 to work alongside, or go dual socket and a bit less DDR5 memory.

Re: Asus Ascent GX10

#158

Post by canucker2016 » Mon, Nov 10, 2025, 9:13 PM UTC

Dell and Lenovo have product pages for their versions of the DGX Spark.

Dell:

https://www.dell.com/en-us/shop/desktop-computers/dell-pro-m...

- $3,998.99 4TB SSD

- $3,699.00 2TB SSD

Lenovo:

https://www.lenovo.com/us/en/p/workstations/thinkstation-p-s...

- $3,999.00 4TB SSD

https://www.lenovo.com/us/en/p/workstations/thinkstation-p-s...

- $3,539.00 1TB SSD

Re: Asus Ascent GX10

#159

Post by aseipp » Mon, Nov 10, 2025, 9:16 PM UTC

mindcrash wrote: post #150

canucker2016 wrote: post #139

Earlier quoted context omitted.

GMKtec, maker of the EVO-X2 mini-PC that uses a Ryzen AI Max 395+, posted a blog post with a comparison between the DGX Spark and their EVO-X2 miniPC. from https://www.gmktec.com/blog/evo-x2-vs-nvidia-dgx-spark-redef... (text taken from https://wccftech.com/forget-nvidia-dgx-spark-amd-strix-halo-... since the GMKtec table was an image, but wccftech converted to an HTML table - EDIT-reformatted to make table look nice…

And additionally Framework apparently benchmarked GPT-OSS 120B (!) on the maxed out 395+ Desktop and reached a 38.0 tok/sec Generation Speed. Given that Nvidia can't even keep up on a 20B model, I assume they can't keep up on the 120B model aswell. https://frame.work/nl/en/desktop?tab=machine-learning So to me the only thing which seems to be interesting about the Spark atm is the ability to daisy link several units…

Unfortunately comparing tok/sec right now in a vacuum and especially across weeks of time is kind of pointless. Everything is still evolving; there were patches within days that bumped GB10 performance by double digit percentiles in some frameworks. You just kind of have to accept things are a moving target.

For comparison, as of right now, I can run GPT-OSS 120b @ 59 tok/sec, using llama.cpp (revision 395e286bc) and Unsloth dynamic 4-bit quantized models.[1] GPT-OSS 20b @ 88 tok/sec [2]. The MXFP4 variant comes in the same, at ~89 tok/sec[3]. It's probably faster on other frameworks, llama.cpp is known to not be the fastest. I don't know what LM Studio backend they used. All of these numbers put the GB10 well ahead of Strix Halo, if only going by the numbers we see here.

If the AMD software wasn't also comparatively optimized by the same amount in the same timeframe, then the GB10 would be faster, now. Maybe it was optimized just as much; I don't have a Strix Halo part to compare. But my point is, don't just compare numbers from two various points in time, it's going to be very misleading.

[1]: https://huggingface.co/unsloth/gpt-oss-120b-GGUF/tree/main/U... [2]: https://huggingface.co/unsloth/gpt-oss-20b-GGUF/resolve/main... [3]: https://huggingface.co/unsloth/gpt-oss-20b-GGUF/resolve/main...

Re: Asus Ascent GX10

#160

Post by aseipp » Mon, Nov 10, 2025, 9:22 PM UTC

hamdingers wrote: post #28

simlevesque wrote: post #23

Earlier quoted context omitted.

gpt-oss:120b https://til.simonwillison.net/llms/codex-spark-gpt-oss

Am I missing it or is there no information about performance? Looking for a tokens/sec

Right now I get 59 tok/sec on GPT-OSS 120B using Unsloth's dynamic 4-bit quants, via llama.cpp https://news.ycombinator.com/item?id=45881049