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…4950525455…104

Comments

  • @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    I'be tried some local LLM's more tha a year ago, but the speed was low, the laptop was going slow, so I gave up.

  • Count me in for the main giveaway! Picked up the 1 GB KVM Black Friday plan in LA DC03 - still the best value around. Thanks for the giveaways, Dustin!

  • lovelyserverlovelyserver Member
    edited November 20

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I don't know now, I am not updated. But few months ago, when I wanted API, Gemini and OpenAi had limited tiers. I haven't used them, anyway, because I stayed on the chat options, just to avoid any unwanted payments.

  • TrKTrK Veteran

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I don't know now, I am not updated. But few months ago, when I wanted API, Gemini and OpenAi had limited tiers. I haven't used them, anyway, because I stayed on the chat options, just to avoid any unwanted payments.

    Lol

    Thanked by 1lovelyserver
  • MrEdMrEd Member

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I tried using free Gemini API (you have to create a project and create API key), but I constantly was getting "is busy right now" and hit the limits all the time. Switching between models was not fun for sure.

  • lovelyserverlovelyserver Member
    edited November 20

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I don't know now, I am not updated. But few months ago, when I wanted API, Gemini and OpenAi had limited tiers. I haven't used them, anyway, because I stayed on the chat options, just to avoid any unwanted payments.

    Lol

    I know... I pay for dedicated servers but I am afraid of some LLM's bills. We all have some weirdness and fears :smiley:

  • MrEdMrEd Member

    @hackersong said:
    Count me in for the main giveaway! Picked up the 1 GB KVM Black Friday plan in LA DC03 - still the best value around. Thanks for the giveaways, Dustin!

    You could have clicked an aff link in Stats page. https://racknerd.projecthive.eu/data This doesn't cost you anything but you would support the developments of all the nice features we get here :)

  • @MrEd how often does stats refresh?

  • MrEdMrEd Member

    @lovelyserver said:
    @MrEd how often does stats refresh?

    Every 5 minutes. You don't have to refresh, new data is loaded automatically ;)

  • TrKTrK Veteran

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I don't know now, I am not updated. But few months ago, when I wanted API, Gemini and OpenAi had limited tiers. I haven't used them, anyway, because I stayed on the chat options, just to avoid any unwanted payments.

    Lol> @MrEd said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I tried using free Gemini API (you have to create a project and create API key), but I constantly was getting "is busy right now" and hit the limits all the time. Switching between models was not fun for sure.

    I tried that and was not so good experience for me, was an option for a trial with $300 for a month but giving my cc info for that was something I would refrain.

  • MrEdMrEd Member

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I don't know now, I am not updated. But few months ago, when I wanted API, Gemini and OpenAi had limited tiers. I haven't used them, anyway, because I stayed on the chat options, just to avoid any unwanted payments.

    Lol> @MrEd said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I tried using free Gemini API (you have to create a project and create API key), but I constantly was getting "is busy right now" and hit the limits all the time. Switching between models was not fun for sure.

    I tried that and was not so good experience for me, was an option for a trial with $300 for a month but giving my cc info for that was something I would refrain.

    I also didn't give my cc info. :)

    Thanked by 1lovelyserver
  • dmaxdmax Member

  • Hello,
    Please double the bandwidth!
    Order #9268683321
    Thanks!

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

  • @MrEd said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I don't know now, I am not updated. But few months ago, when I wanted API, Gemini and OpenAi had limited tiers. I haven't used them, anyway, because I stayed on the chat options, just to avoid any unwanted payments.

    Lol> @MrEd said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I tried using free Gemini API (you have to create a project and create API key), but I constantly was getting "is busy right now" and hit the limits all the time. Switching between models was not fun for sure.

    I tried that and was not so good experience for me, was an option for a trial with $300 for a month but giving my cc info for that was something I would refrain.

    I also didn't give my cc info. :)

    Smart! No CC details. No no! No way.

  • DocZDocZ Member

    Happy customer here. GLWS

    Thanked by 1lovelyserver
  • DocZDocZ Member

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

  • lovelyserverlovelyserver Member
    edited November 20

    @DocZ said:
    Happy customer here. GLWS

    Hiya!

    Happy customer here too.

    Enjoy the RACKNERD Black Fridat Party Thread!

  • HAPPY RN CUSTOMERS GANG!

  • OrderID:7059355222

  • Hi
    I'd like to request double bandwidth for my Black Friday VPS. Thanks!
    Invoice #26966437

  • @MrEd said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I don't know now, I am not updated. But few months ago, when I wanted API, Gemini and OpenAi had limited tiers. I haven't used them, anyway, because I stayed on the chat options, just to avoid any unwanted payments.

    Lol> @MrEd said:

    @TrK said:

    @lovelyserver said:

    @TrK said:

    @lovelyserver said:

    @noob404 said:
    TrK, you running any small open weight LLMs on your homelab?

    Do you think is better to run small LLMs locally instead of benefit of free web plans?

    Can you list some free web plans?

    I mean free tiers

    Here are some AI chat services with free tiers:

    ChatGPT
    Claude
    Google Gemini
    Perplexity
    Microsoft Copilot

    It is better to run something small locally instead of using the free ones? I'm thinking of speed. That's why. And also hardware capabilities.

    For me, just generating text and other questions, free web chat is enough.

    Any comes with free API?

    I tried using free Gemini API (you have to create a project and create API key), but I constantly was getting "is busy right now" and hit the limits all the time. Switching between models was not fun for sure.

    I tried that and was not so good experience for me, was an option for a trial with $300 for a month but giving my cc info for that was something I would refrain.

    I also didn't give my cc info. :)

    I am currently using Gemini API. If I choose any other model than gemini-3.5-flash-lite, I keep hitting 429 or 503 very often.

    Thanked by 1lovelyserver
  • Hi Dustin, just ordered the 2.5 GB Black Friday VPS! Please double my bandwidth. Order #: 2364622402. Thank you!

  • Any chance we'll see a Europe location in this Black Friday round? I've been holding off on picking a config until I know whether something closer to EU is coming.

  • Thanks RackNerd for the Black Friday giveaway! Good luck everyone!

  • Hello, I would like to double the bandwidth.
    Order Number: 2037366199
    Invoice #26909419
    Thanks!

  • @zwx12581 said:
    Thanks RackNerd for the Black Friday giveaway! Good luck everyone!

    Good luck to you as well!

  • Great!!

  • zzhe810zzhe810 Member
    edited November 20

    RackNerd - Order Number is: 6118030206

Sign In or Register to comment.