Howdy, Stranger!

It looks like you're new here. If you want to get involved, click one of these buttons!


New on LowEndTalk? Please Register and read our Community Rules.

All new Registrations are manually reviewed and approved, so a short delay after registration may occur before your account becomes active.

RackNerd’s BLACK FRIDAY TAKEOVER! NEW DEALS, NEW TECH, AdminBolt HOSTING + HUNDREDS OF GIVEAWAYS!

1…2526283031…103

Comments

  • I have experimented with local AI as well, nothing serious yet though, but I was running CPU inference on models less than 32b. They are impressive but without a GPU, painfully slow for the most part.

  • Jamie96Jamie96 Member
    edited November 20

    @noob404 said:

    @Jamie96 said:
    So, I understand how a provider like this manages to get these prices. That's not a problem. But anyone that has one, maybe even cut to the chase and anyone that has one in Ashburn, what CPU are they using to fuel this offer, and otherwise how's your performance so far? I thought I'd ask here for the real user reviews and because RackNerd's sales chat is understandable overwhelmed right now so I can't ask them anything. I am getting one from this offer but I'm trying to temper my expectations and make sure I get the right one since there's no refund policy.

    My goal is docker apps, a variety of them as I find myself in a bleak economy not really looking forward to paying repair costs on a homelab. So docker, all sorts, a Postgres or two as they require. Thinking of going all the way for the memory but I'll be sad to find the CPU is lackluster and I should have gotten multiple smaller ones to spread the nodes.

    TL;DR, users what CPU you got, how's it going, would you think I survive on one monolith VPS or prefer split load?

    For your purposes, I'd recommend considering RackNerd's Ryzen VPSes. https://www.racknerd.com/ryzen-vps

    That bad, huh? I'll assume decade old Xeons then, the original budget driver. Not a dealbreaker mind, since the Ryzen of same RAM for example is a 400% increase in cost for less vCores and everything else...

  • @dahartigan said:
    Toronto! Interesting.. a new location on the way?

    Seems there was a giveaway 4GB RAM VPS for 1 year in Toronto a few pages back.

  • LET’S GO! RACKNERD BLACK FRIDAY 2026 IS LIVE: https://www.racknerd.com/BlackFriday/ ⚡

  • LET’S GO! RACKNERD BLACK FRIDAY 2026 IS LIVE: https://www.racknerd.com/BlackFriday/ ⚡

  • @op23 said:

    @DaDeveloper said:
    As a side note for peeps that are still awake and kicking, Local AI is badass! Had a agent working for damn near 24 hours straightht off of my hardware and Hermes agent, and its used over 498M tokens in input and 4.5M in output and it only cost me electricity and saved me time of doing what its doin. that and I don't have to worry about big bro snooping or a company harvesting my data. Soon I will be moving off of Hermes tho.

    It’s between paying $20 for a vibecoded generic website through Claude and $12000 to do the same thing locally by buying a GPU. Or lots of ram (slower option). Yeah I think I’ll let big brother snoop into the 157373373737th react offering.

    1. Not using it to vibe code anything
    2. Cost does not matter as much for me compared to no caps, convenience, data sovereignty and privacy
    3. It generates things faster than I could have done them on my own
    4. IT allows me to get tasks done when I am working my day job so that I can spend time doing what I love and enjoy rather than these tasks
    5. What does react have to do with it? I wouldn't have used react anyways... it sucks
  • @Jamie96 said:

    @noob404 said:

    @Jamie96 said:
    So, I understand how a provider like this manages to get these prices. That's not a problem. But anyone that has one, maybe even cut to the chase and anyone that has one in Ashburn, what CPU are they using to fuel this offer, and otherwise how's your performance so far? I thought I'd ask here for the real user reviews and because RackNerd's sales chat is understandable overwhelmed right now so I can't ask them anything. I am getting one from this offer but I'm trying to temper my expectations and make sure I get the right one since there's no refund policy.

    My goal is docker apps, a variety of them as I find myself in a bleak economy not really looking forward to paying repair costs on a homelab. So docker, all sorts, a Postgres or two as they require. Thinking of going all the way for the memory but I'll be sad to find the CPU is lackluster and I should have gotten multiple smaller ones to spread the nodes.

    TL;DR, users what CPU you got, how's it going, would you think I survive on one monolith VPS or prefer split load?

    For your purposes, I'd recommend considering RackNerd's Ryzen VPSes. https://www.racknerd.com/ryzen-vps

    That bad, huh? I'll assume decade old Xeons then, the original budget driver.

    Not my point. I have used both the Xeons and Ryzens from RackNerd. Some of my projects were really happy on the Xeons, but I can't remember which versions there, only remember I never faced any issues with them.

    I moved to their Ryzen cause I got a good deal a few years ago. I just meant if you can get the Ryzen go for it. Else, the Intel-based VPSes from RackNerd will also serve your purpose well.

    Thanked by 1Jamie96
  • @noob404 said:

    @op23 said:

    @DaDeveloper said:
    As a side note for peeps that are still awake and kicking, Local AI is badass! Had a agent working for damn near 24 hours straightht off of my hardware and Hermes agent, and its used over 498M tokens in input and 4.5M in output and it only cost me electricity and saved me time of doing what its doin. that and I don't have to worry about big bro snooping or a company harvesting my data. Soon I will be moving off of Hermes tho.

    It’s between paying $20 for a vibecoded generic website through Claude and $12000 to do the same thing locally by buying a GPU. Or lots of ram (slower option). Yeah I think I’ll let big brother snoop into the 157373373737th react offering.

    @DaDeveloper What's your machine spec like and what model did you use?

  • @DaDeveloper said:

    @noob404 said:

    @op23 said:

    @DaDeveloper said:
    As a side note for peeps that are still awake and kicking, Local AI is badass! Had a agent working for damn near 24 hours straightht off of my hardware and Hermes agent, and its used over 498M tokens in input and 4.5M in output and it only cost me electricity and saved me time of doing what its doin. that and I don't have to worry about big bro snooping or a company harvesting my data. Soon I will be moving off of Hermes tho.

    It’s between paying $20 for a vibecoded generic website through Claude and $12000 to do the same thing locally by buying a GPU. Or lots of ram (slower option). Yeah I think I’ll let big brother snoop into the 157373373737th react offering.

    @DaDeveloper What's your machine spec like and what model did you use?

    I think you missed to add the message

  • LET’S GO! RACKNERD BLACK FRIDAY 2026 IS LIVE: https://www.racknerd.com/BlackFriday/ ⚡

  • @noob404 said:

    @dahartigan said:
    Toronto! Interesting.. a new location on the way?

    Seems there was a giveaway 4GB RAM VPS for 1 year in Toronto a few pages back.

    Yeah that's what I just saw and noticed the location. They don't have anything in stock in Toronto right now, not even dedicated servers.

    It's been about a year since Toronto has been in stock (source: https://racknerdtracker.com/?q=Toronto&stock=0 including out of stock)

    Thanked by 1noob404
  • @noob404 said:

    @op23 said:

    @DaDeveloper said:
    As a side note for peeps that are still awake and kicking, Local AI is badass! Had a agent working for damn near 24 hours straightht off of my hardware and Hermes agent, and its used over 498M tokens in input and 4.5M in output and it only cost me electricity and saved me time of doing what its doin. that and I don't have to worry about big bro snooping or a company harvesting my data. Soon I will be moving off of Hermes tho.

    It’s between paying $20 for a vibecoded generic website through Claude and $12000 to do the same thing locally by buying a GPU. Or lots of ram (slower option). Yeah I think I’ll let big brother snoop into the 157373373737th react offering.

    @DaDeveloper What's your machine spec like and what model did you use?

    Combined Specs (Two 128 GB Units)

    • AI Compute: Up to 2 PFLOPS (FP4 with sparsity); 12,288 total CUDA cores (6,144 per unit)
    • CPUs: 40 total Arm cores (two 20-core processors, each with 10 Cortex-X925 + 10 Cortex-A725)
    • Memory: 256 GB aggregate LPDDR5x unified memory across two nodes (128 GB per unit; 273 GB/s bandwidth per node, 546 GB/s aggregate)
    • Model Capacity: Supports models up to ~400B–405B parameters across distributed workloads

    As for the model I am still using Deepseek v4 flash 0731 due to slow internet but It hasn't failed any tasks yet

    Thanked by 2noob404 op23
  • LET’S GO! RACKNERD BLACK FRIDAY 2026 IS LIVE: https://www.racknerd.com/BlackFriday/ ⚡

  • @dahartigan said:

    @noob404 said:

    @dahartigan said:
    Toronto! Interesting.. a new location on the way?

    Seems there was a giveaway 4GB RAM VPS for 1 year in Toronto a few pages back.

    Yeah that's what I just saw and noticed the location. They don't have anything in stock in Toronto right now, not even dedicated servers.

    It's been about a year since Toronto has been in stock (source: https://racknerdtracker.com/?q=Toronto&stock=0 including out of stock)

    Ah yes. I believe we will have a few more though rare during the flash sales on BF.

  • LET’S GO! RACKNERD BLACK FRIDAY 2026 IS LIVE: https://www.racknerd.com/BlackFriday/ ⚡

  • op23op23 Member

    @DaDeveloper said:

    @op23 said:

    @DaDeveloper said:
    As a side note for peeps that are still awake and kicking, Local AI is badass! Had a agent working for damn near 24 hours straightht off of my hardware and Hermes agent, and its used over 498M tokens in input and 4.5M in output and it only cost me electricity and saved me time of doing what its doin. that and I don't have to worry about big bro snooping or a company harvesting my data. Soon I will be moving off of Hermes tho.

    It’s between paying $20 for a vibecoded generic website through Claude and $12000 to do the same thing locally by buying a GPU. Or lots of ram (slower option). Yeah I think I’ll let big brother snoop into the 157373373737th react offering.

    1. Not using it to vibe code anything
    2. Cost does not matter as much for me compared to no caps, convenience, data sovereignty and privacy
    3. It generates things faster than I could have done them on my own
    4. IT allows me to get tasks done when I am working my day job so that I can spend time doing what I love and enjoy rather than these tasks
    5. What does react have to do with it? I wouldn't have used react anyways... it sucks

    Just curious, what else are you doing/generating and what are your machine specs? I am not stranger to AI (use it at my day job and during personal projects), but I am also not rich to buy hardware for anything better than a 9b that fits in locally. And during my playing with a 27b model I was very disappointed.

  • @DaDeveloper said:

    @noob404 said:

    @op23 said:

    @DaDeveloper said:
    As a side note for peeps that are still awake and kicking, Local AI is badass! Had a agent working for damn near 24 hours straightht off of my hardware and Hermes agent, and its used over 498M tokens in input and 4.5M in output and it only cost me electricity and saved me time of doing what its doin. that and I don't have to worry about big bro snooping or a company harvesting my data. Soon I will be moving off of Hermes tho.

    It’s between paying $20 for a vibecoded generic website through Claude and $12000 to do the same thing locally by buying a GPU. Or lots of ram (slower option). Yeah I think I’ll let big brother snoop into the 157373373737th react offering.

    @DaDeveloper What's your machine spec like and what model did you use?

    Combined Specs (Two 128 GB Units)

    • AI Compute: Up to 2 PFLOPS (FP4 with sparsity); 12,288 total CUDA cores (6,144 per unit)
    • CPUs: 40 total Arm cores (two 20-core processors, each with 10 Cortex-X925 + 10 Cortex-A725)
    • Memory: 256 GB aggregate LPDDR5x unified memory across two nodes (128 GB per unit; 273 GB/s bandwidth per node, 546 GB/s aggregate)
    • Model Capacity: Supports models up to ~400B–405B parameters across distributed workloads

    As for the model I am still using Deepseek v4 flash 0731 due to slow internet but It hasn't failed any tasks yet

    Awesome. I am confused. Is this a Snapdragon AI processor?

  • op23op23 Member
    edited November 20

    @DaDeveloper said:

    @noob404 said:

    @op23 said:

    @DaDeveloper said:
    As a side note for peeps that are still awake and kicking, Local AI is badass! Had a agent working for damn near 24 hours straightht off of my hardware and Hermes agent, and its used over 498M tokens in input and 4.5M in output and it only cost me electricity and saved me time of doing what its doin. that and I don't have to worry about big bro snooping or a company harvesting my data. Soon I will be moving off of Hermes tho.

    It’s between paying $20 for a vibecoded generic website through Claude and $12000 to do the same thing locally by buying a GPU. Or lots of ram (slower option). Yeah I think I’ll let big brother snoop into the 157373373737th react offering.

    @DaDeveloper What's your machine spec like and what model did you use?

    Combined Specs (Two 128 GB Units)

    • AI Compute: Up to 2 PFLOPS (FP4 with sparsity); 12,288 total CUDA cores (6,144 per unit)
    • CPUs: 40 total Arm cores (two 20-core processors, each with 10 Cortex-X925 + 10 Cortex-A725)
    • Memory: 256 GB aggregate LPDDR5x unified memory across two nodes (128 GB per unit; 273 GB/s bandwidth per node, 546 GB/s aggregate)
    • Model Capacity: Supports models up to ~400B–405B parameters across distributed workloads

    As for the model I am still using Deepseek v4 flash 0731 due to slow internet but It hasn't failed any tasks yet

    Wish I was this rich. I am jealous, but yeah, that looks lots of fun. Enjoy!

  • BTW, I am genuinely curious as to why no one on LET is talking about GTA VI. Not that I have played or planning to play it, but it's the buzz all around.

  • @op23 said:

    @DaDeveloper said:

    @noob404 said:

    @op23 said:

    @DaDeveloper said:
    As a side note for peeps that are still awake and kicking, Local AI is badass! Had a agent working for damn near 24 hours straightht off of my hardware and Hermes agent, and its used over 498M tokens in input and 4.5M in output and it only cost me electricity and saved me time of doing what its doin. that and I don't have to worry about big bro snooping or a company harvesting my data. Soon I will be moving off of Hermes tho.

    It’s between paying $20 for a vibecoded generic website through Claude and $12000 to do the same thing locally by buying a GPU. Or lots of ram (slower option). Yeah I think I’ll let big brother snoop into the 157373373737th react offering.

    @DaDeveloper What's your machine spec like and what model did you use?

    Combined Specs (Two 128 GB Units)

    • AI Compute: Up to 2 PFLOPS (FP4 with sparsity); 12,288 total CUDA cores (6,144 per unit)
    • CPUs: 40 total Arm cores (two 20-core processors, each with 10 Cortex-X925 + 10 Cortex-A725)
    • Memory: 256 GB aggregate LPDDR5x unified memory across two nodes (128 GB per unit; 273 GB/s bandwidth per node, 546 GB/s aggregate)
    • Model Capacity: Supports models up to ~400B–405B parameters across distributed workloads

    As for the model I am still using Deepseek v4 flash 0731 due to slow internet but It hasn't failed any tasks yet

    Wish I was this rich.

    Me too. I am running on 32GB RAM, no GPU

  • op23op23 Member

    @noob404 said:

    @DaDeveloper said:

    @noob404 said:

    @op23 said:

    @DaDeveloper said:
    As a side note for peeps that are still awake and kicking, Local AI is badass! Had a agent working for damn near 24 hours straightht off of my hardware and Hermes agent, and its used over 498M tokens in input and 4.5M in output and it only cost me electricity and saved me time of doing what its doin. that and I don't have to worry about big bro snooping or a company harvesting my data. Soon I will be moving off of Hermes tho.

    It’s between paying $20 for a vibecoded generic website through Claude and $12000 to do the same thing locally by buying a GPU. Or lots of ram (slower option). Yeah I think I’ll let big brother snoop into the 157373373737th react offering.

    @DaDeveloper What's your machine spec like and what model did you use?

    Combined Specs (Two 128 GB Units)

    • AI Compute: Up to 2 PFLOPS (FP4 with sparsity); 12,288 total CUDA cores (6,144 per unit)
    • CPUs: 40 total Arm cores (two 20-core processors, each with 10 Cortex-X925 + 10 Cortex-A725)
    • Memory: 256 GB aggregate LPDDR5x unified memory across two nodes (128 GB per unit; 273 GB/s bandwidth per node, 546 GB/s aggregate)
    • Model Capacity: Supports models up to ~400B–405B parameters across distributed workloads

    As for the model I am still using Deepseek v4 flash 0731 due to slow internet but It hasn't failed any tasks yet

    Awesome. I am confused. Is this a Snapdragon AI processor?

    DGX spark or similar

    Thanked by 1noob404
  • Order Number: 5020484975, please double my bandwidth on both orders. Thanks!

  • @op23 said:

    @noob404 said:

    @DaDeveloper said:

    @noob404 said:

    @op23 said:

    @DaDeveloper said:
    As a side note for peeps that are still awake and kicking, Local AI is badass! Had a agent working for damn near 24 hours straightht off of my hardware and Hermes agent, and its used over 498M tokens in input and 4.5M in output and it only cost me electricity and saved me time of doing what its doin. that and I don't have to worry about big bro snooping or a company harvesting my data. Soon I will be moving off of Hermes tho.

    It’s between paying $20 for a vibecoded generic website through Claude and $12000 to do the same thing locally by buying a GPU. Or lots of ram (slower option). Yeah I think I’ll let big brother snoop into the 157373373737th react offering.

    @DaDeveloper What's your machine spec like and what model did you use?

    Combined Specs (Two 128 GB Units)

    • AI Compute: Up to 2 PFLOPS (FP4 with sparsity); 12,288 total CUDA cores (6,144 per unit)
    • CPUs: 40 total Arm cores (two 20-core processors, each with 10 Cortex-X925 + 10 Cortex-A725)
    • Memory: 256 GB aggregate LPDDR5x unified memory across two nodes (128 GB per unit; 273 GB/s bandwidth per node, 546 GB/s aggregate)
    • Model Capacity: Supports models up to ~400B–405B parameters across distributed workloads

    As for the model I am still using Deepseek v4 flash 0731 due to slow internet but It hasn't failed any tasks yet

    Awesome. I am confused. Is this a Snapdragon AI processor?

    DGX spark or similar

    Didn't know DGX was ARM.

  • Yep two dgx sparks

    Thanked by 1noob404
  • At this point, is it better to get gaming GPUs or NPUs like Ryzen AI Max for local LLM inference?

  • @DaDeveloper said:
    Yep two dgx sparks

    How big of a hole did it burn in your pockets?

  • Hello, I would like to double my bandwidth. Invoice #26921412 Thanks!

  • And does anyone have experience with Alibaba Cloud for DeepSeek 4? Any good?

  • @noob404 said:

    @Jamie96 said:

    @noob404 said:

    @Jamie96 said:
    So, I understand how a provider like this manages to get these prices. That's not a problem. But anyone that has one, maybe even cut to the chase and anyone that has one in Ashburn, what CPU are they using to fuel this offer, and otherwise how's your performance so far? I thought I'd ask here for the real user reviews and because RackNerd's sales chat is understandable overwhelmed right now so I can't ask them anything. I am getting one from this offer but I'm trying to temper my expectations and make sure I get the right one since there's no refund policy.

    My goal is docker apps, a variety of them as I find myself in a bleak economy not really looking forward to paying repair costs on a homelab. So docker, all sorts, a Postgres or two as they require. Thinking of going all the way for the memory but I'll be sad to find the CPU is lackluster and I should have gotten multiple smaller ones to spread the nodes.

    TL;DR, users what CPU you got, how's it going, would you think I survive on one monolith VPS or prefer split load?

    For your purposes, I'd recommend considering RackNerd's Ryzen VPSes. https://www.racknerd.com/ryzen-vps

    That bad, huh? I'll assume decade old Xeons then, the original budget driver.

    Not my point. I have used both the Xeons and Ryzens from RackNerd. Some of my projects were really happy on the Xeons, but I can't remember which versions there, only remember I never faced any issues with them.

    I moved to their Ryzen cause I got a good deal a few years ago. I just meant if you can get the Ryzen go for it. Else, the Intel-based VPSes from RackNerd will also serve your purpose well.

    I mean I don't disagree with you, and if they put the Ryzen's on sale that would be good, but as of today it's a 400% increase along the same RAM line with less cores, storage, etc....of course those less quantity cores are probably orders of magnitude better at the job..and it's not a critical or profitable workload so I'm hard pressed to justify all costs, hence the deal hunting and interest in what the sacrifices are to get to this cost.

    Alright, for anyone following along I did get a quick bite from sales, they've got a mix of Xeon 2680 V2s and Gold 6252. So some old and some newer, luck of the draw.

    Thanked by 1noob404
  • Order Number: 9900760405
    Please double the transfer.
    Thank you!

Sign In or Register to comment.