Slickdeals is community-supported.Ā  We may get paid by brands for deals, including promoted items.
Heads up, this deal has expired. Want to create a deal alert for this item?
expiredSuryasis posted Mar 28, 2026 03:22 AM
expiredSuryasis posted Mar 28, 2026 03:22 AM

Asrock Intel Arc Pro B70 256 Bit 32GB GDDR6 PCIe 5.0 x16 Workstation Graphics Card @ $1000 (Back Ordered) + F/S

$1,000

Newegg
6,415 Views
Visit Newegg
Good Deal
Save
Share
Deal Details
Link: https://www.newegg.com/asrock-b70...6814930149

ETA Date: 4/3/2026.

Spec:
  • Asrock B70 CT Arc Pro B70 Graphics Card
  • 32GB 256 Bit GDDR6 Memory
  • 32 IntelĀ® Xe2-HPG Cores
  • 256 XMX AI Engines (IntelĀ® Xe Matrix eXtensions)
  • 32 RT Cores
  • 2540 MHz GPU Clock
  • 19 Gbps Memory Speed
  • 608 GB/s Bandwidth
  • 1x 12V-2x6-pin Power Connector
  • I/O:
    • 1x DisplayPortā„¢ 2.1 (Primary, up to UHBR13.5)
    • 3x DisplayPortā„¢ 2.1 (up to UHBR10)
Product Info
Community Notes
About the Poster
Deal Details
Product Info
Community Notes
About the Poster
Link: https://www.newegg.com/asrock-b70...6814930149

ETA Date: 4/3/2026.

Spec:
  • Asrock B70 CT Arc Pro B70 Graphics Card
  • 32GB 256 Bit GDDR6 Memory
  • 32 IntelĀ® Xe2-HPG Cores
  • 256 XMX AI Engines (IntelĀ® Xe Matrix eXtensions)
  • 32 RT Cores
  • 2540 MHz GPU Clock
  • 19 Gbps Memory Speed
  • 608 GB/s Bandwidth
  • 1x 12V-2x6-pin Power Connector
  • I/O:
    • 1x DisplayPortā„¢ 2.1 (Primary, up to UHBR13.5)
    • 3x DisplayPortā„¢ 2.1 (up to UHBR10)

Community Voting

Deal Score
+14
Good Deal
Visit Newegg

Price Intelligence

Model: ASRock B70 Intel Arc Pro B70 B70 CT 32GB 256-bit GDDR6 PCI Express 5.0 x16 2-slot Graphics Card

Deal HistoryĀ 

Sale Price
Slickdeal
  • $NaN
  • Today

Current Prices

Sort: Lowest to Highest | Last Updated 5/31/2026, 01:18 AM
Sold By Sale Price
NewEgg$999.99

Leave a Comment

Unregistered (You)

19 Comments

Sign up for a Slickdeals account to remove this ad.

Mar 28, 2026 03:27 AM
357 Posts
Joined Dec 2017
EthanH5438Mar 28, 2026 03:27 AM
357 Posts
Is it closer to a 3090?
Original Poster
Pro
Expert
This user is an Expert in Computers
Mar 28, 2026 03:43 AM
20,527 Posts
Joined Jul 2015
SuryasisMar 28, 2026 03:43 AM
Original Poster
Pro
Expert
This user is an Expert in Computers
20,527 Posts

Our community has rated this post as helpful. If you agree, why not thank Suryasis

Quote from EthanH5438 :
Is it closer to a 3090?
In gaming performance, probably not. This is targeted as a Workstation/LLM Interencing Graphics card an on that regards, it is better than most cards at this price bracket.
6
Mar 28, 2026 04:30 AM
824 Posts
Joined Dec 2010
TMA-1Mar 28, 2026 04:30 AM
824 Posts
Quote from Suryasis :
In gaming performance, probably not. This is targeted as a Workstation/LLM Interencing Graphics card an on that regards, it is better than most cards at this price bracket.
Out of curiosity, what type of scale would you need where moving to a co-located or cloud (AWS, Azure, Oracle, etc) is cheaper than on-prem systems for LLMs?
Mar 28, 2026 04:40 AM
1,215 Posts
Joined Feb 2007
cheshirecatMar 28, 2026 04:40 AM
1,215 Posts
Does it support tensor parallelism? Full Linux support? (B60 was weirdly favoring Windows)
Original Poster
Pro
Expert
This user is an Expert in Computers
Mar 28, 2026 05:37 AM
20,527 Posts
Joined Jul 2015
SuryasisMar 28, 2026 05:37 AM
Original Poster
Pro
Expert
This user is an Expert in Computers
20,527 Posts

Our community has rated this post as helpful. If you agree, why not thank Suryasis

Quote from cheshirecat :
Does it support tensor parallelism? Full Linux support? (B60 was weirdly favoring Windows)
Yes it does, and especially excels in AI Inferencing. Check this Video: -
https://www.youtube.com/watch?v=DTJr2msyqGY&t=2s
You can literally stack multiple of this GPU in a Server and they can work together to handle multiple prompts coming from users. And Linux Support is full. However, keep in mind, Intel has been updating their stack regularly but it is still far behind CUDA and even AMD ROCm. The model supports are not the lastest one most of the times, you need to work with slightly older version which is compatible with Intel Software stack.
4
Original Poster
Pro
Expert
This user is an Expert in Computers
Mar 28, 2026 05:37 AM
20,527 Posts
Joined Jul 2015
SuryasisMar 28, 2026 05:37 AM
Original Poster
Pro
Expert
This user is an Expert in Computers
20,527 Posts
Quote from TMA-1 :
Out of curiosity, what type of scale would you need where moving to a co-located or cloud (AWS, Azure, Oracle, etc) is cheaper than on-prem systems for LLMs?
I'm no expert on this but if you can clarify your ask in a bit details then I can try to answer.
Mar 28, 2026 01:15 PM
2,050 Posts
Joined Jul 2010
jackharvestMar 28, 2026 01:15 PM
2,050 Posts
As soon as I can run a mini Claude locally with a gargantuan context window, I'll buy this instantly.

Sign up for a Slickdeals account to remove this ad.

Mar 28, 2026 10:52 PM
690 Posts
Joined Sep 2019
UniqueSoda2365Mar 28, 2026 10:52 PM
690 Posts
Correct me if im wrong, but NVIDIA is still much better and easier for all Local model stuff right?

Last I checked, there's a reason Nvidia cards cost so much more at the moment.
Mar 28, 2026 10:59 PM
1,751 Posts
Joined Oct 2015
JimR2075Mar 28, 2026 10:59 PM
1,751 Posts
Quote from UniqueSoda2365 :
Correct me if im wrong, but NVIDIA is still much better and easier for all Local model stuff right?

Last I checked, there's a reason Nvidia cards cost so much more at the moment.
I don't know about 'easier', but this card is supposed to be equal performance of nVidia cards that cost twice as much. So if reports are true, this is 1/2 the price vs Nvidia.
Mar 29, 2026 12:22 AM
6,094 Posts
Joined Jan 2007
Evan55Mar 29, 2026 12:22 AM
6,094 Posts
Anyone accustomed to using the latest chatGPT or Claude or Gemini will be very disappointed with an open model that can fit in 32gb of vram.
1
3
Pro
Mar 29, 2026 02:32 AM
959 Posts
Joined Jun 2006
zyberwoof
Pro
Mar 29, 2026 02:32 AM
959 Posts
Quote from UniqueSoda2365 :
Correct me if im wrong, but NVIDIA is still much better and easier for all Local model stuff right?

Last I checked, there's a reason Nvidia cards cost so much more at the moment.
NVIDIA has much more community support.

Think of it like right vs left-handed. Neither is inherently better than the other. But, since most people are right-handed, a lot of things are designed specifically for right-handed people. Aside from specialized cases like baseball or feeling pride in being unique, life is easier if your are right handed.

NVIDIA has a much higher percentage of the GPU market. A lot more people are experts with NVIDIA hardware and software than AMD or Intel. This means more software is specifically designed around NVIDIA hardware. And since there is more software support for NVIDIA hardware, NVIDIA hardware becomes more valuable.

Is NVIDIA hardware actually more advanced or more capable? I'd guess "no". Or at least, it isn't a clear "yes". Not because I know a lot about GPUs. Just because it normally happens that when a company gets that much of a lead in the market. They tend to get much more complacent.
1
1
Mar 29, 2026 08:37 AM
1,092 Posts
Joined Feb 2017
theshopper2022Mar 29, 2026 08:37 AM
1,092 Posts
Tempted for Local AI. MSRP is meant to be $949, but the scalpers will probably push theprice higher
Mar 29, 2026 11:50 AM
104 Posts
Joined Aug 2023
OodlesofNoodles157Mar 29, 2026 11:50 AM
104 Posts
Quote from theshopper2022 :
Tempted for Local AI. MSRP is meant to be $949, but the scalpers will probably push theprice higher
If by scalpers, you mean Newegg cashing in by pricing this GPU higher at it's release, then yes Newegg is scalping.
Mar 29, 2026 02:37 PM
824 Posts
Joined Dec 2010
TMA-1Mar 29, 2026 02:37 PM
824 Posts
Quote from Suryasis :
I'm no expert on this but if you can clarify your ask in a bit details then I can try to answer.
Probably too complex of a question of this forum but if someone is training LLMs where is the inflection point when it's cheaper to train your LLM in the cloud (using AWS, etc.) vs buying your own equipment to train the LLM?

Sign up for a Slickdeals account to remove this ad.

Original Poster
Pro
Expert
This user is an Expert in Computers
Mar 30, 2026 03:04 AM
20,527 Posts
Joined Jul 2015
SuryasisMar 30, 2026 03:04 AM
Original Poster
Pro
Expert
This user is an Expert in Computers
20,527 Posts
Quote from TMA-1 :
Probably too complex of a question of this forum but if someone is training LLMs where is the inflection point when it's cheaper to train your LLM in the cloud (using AWS, etc.) vs buying your own equipment to train the LLM?
What you mean is fine tuning your LLM, by chooisng a pretrained model and then fine tuning it with your data and thatis always going to be cheaper locally but you will be lomited by what you have. 32GB Video memory allows this Graphics Card to use pretty big models , 30B with 8 bit Integer. However, fine tuning needs much higher VAM for same model. Using LoRA / QLoRA Fine-Tuning, you can easily train 13B parameter models with 32GB memory. You can even go higher, nearly 30B but in that case, you need to use 4 Bit Quantization and lot of optimization techniques.
1

Leave a Comment

Unregistered (You)

Popular Deals

Trending Deals