• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

Search results

  1. FrgMstr

    What LLM/Model you using?

    Honesty my insight on that is very limited. Only know what I have tried personally.
  2. FrgMstr

    What LLM/Model you using?

    Laguna can and has. 100% local using Hermes.
  3. FrgMstr

    What LLM/Model you using?

    Get into Hermes. It changes everything. And you can keep it guardrailed easily.
  4. FrgMstr

    What LLM/Model you using?

    Are you using Hermes? Worth noting that Gemma 4 is an OK all-around model, but the key is to pick the model suited for your particular profile/agent's task at hand. For a specific project, I will ask Hermes and Gemini to search for the "best" model for the task. Then build a profile around...
  5. FrgMstr

    Samsung Trio 65w Phone Charger $10.92 Shipped at eBay

    Same here. I don't have any that have two USB-C ports...
  6. FrgMstr

    AI Memes and Funnies

  7. FrgMstr

    AI Memes and Funnies

  8. FrgMstr

    Follow & Unfollow users

    No.
  9. FrgMstr

    Follow & Unfollow users

    "Follow" a user on XenForo forums is a one-way social feature that lets you subscribe to another member’s activity so it shows up in your personalized News Feed. "Unfollow" simply removes that subscription. What “Follow” does... When you click Follow on a user’s profile, member card, or avatar...
  10. FrgMstr

    Dev at id Software says Microsoft 'burned a lot of bridges' in the industry

    I guess a lot of what I said is going over your heads. Yes, I am very aware of the indie game market and where it stands currently. "I think is about to be a renaissance of Indie Games in the gaming industry. " The magnitude of changes from this moment is going to be something new. That is...
  11. FrgMstr

    What LLM/Model you using?

    3.8 is extremely impressive, but painfully slow. I started collecting data this week, moving from Q8 to Q6. Q6 is SLOWER than Q8! Dunno why.... I read a quick X article yesterday that showed Q4 being almost as good as Q8.
  12. FrgMstr

    Samsung Trio 65w Phone Charger $10.92 Shipped at eBay

    I rolled the bones as well on a couple. From the seller's ebay store page, he looks to work in a legit phone retailer...
  13. FrgMstr

    Dev at id Software says Microsoft 'burned a lot of bridges' in the industry

    I think is about to be a renaissance of Indie Games in the gaming industry. Obviously, we have seen a lot of those folks get axed lately. They are not going to stop making games. Also, the fact that no one is the damn world can afford a video card, we are going to see a lot of those games not...
  14. FrgMstr

    Pixel 11 / Pixel 11 Pro / Pixel 11 Pro XL / Pixel 11 Pro Fold

    The fact that phone aesthetics are still a think is confounding to me. All look exactly the same to me.
  15. FrgMstr

    What LLM/Model you using?

    What model?
  16. FrgMstr

    What LLM/Model you using?

    What are you doing with it exactly?
  17. FrgMstr

    This Sub Going Forward - Your Suggestions?

    I try out best to keep our thumb on that. We have systems built in to help us identify before it goes anywhere.
  18. FrgMstr

    DOOM: The Dark Ages

    HA! They are never turning that IP over to anyone else. They would rather mothball it rather than give anyone else the ability to use it.
  19. FrgMstr

    Subforums Now Active

    Thanks for the catch! Fixed.
  20. FrgMstr

    Subforums Now Active

    Topics are split up a bit some so we can organize a bit. If you want a thread moved out of general and into a different sub. Just use the REPORT POST button and tell me where you want it to go.
  21. FrgMstr

    This Sub Going Forward - Your Suggestions?

    We have a bit of reorganization done, let's see how it works out.
  22. FrgMstr

    Cooling an AMD Instinct MI210 for local inference

    My Hermes manager profile.... https://github.com/frgmstr/hermes-manager
  23. FrgMstr

    Cooling an AMD Instinct MI210 for local inference

    LM Studio is SO easy...
  24. FrgMstr

    What LLM/Model you using?

    Qwen 3.8 Smartest I have experienced. Slowest.
  25. FrgMstr

    This Sub Going Forward - Your Suggestions?

    I know we have all "AI" piled into one sub right now. If we broke it down to its own category, what different topic categories would you like to see?
  26. FrgMstr

    DRAM Pricing Jumps 50%, Only 70% of Orders Getting Filled

    Things are going to get worse, before they get worser.
  27. FrgMstr

    Cooling an AMD Instinct MI210 for local inference

    If you want to stay Linux, I would just drop Ubuntu on the machine, Ollama, and Hermes if you want to play with Agentic to keep it simple out of the gate. Or go full Win11 and use Hermes Desktop which is awesome. You are going to find that trying to force your way down the ROCM path with local...
  28. FrgMstr

    General Mayhem

    Right here, tordogs . https://hardforum.com/forums/general-mayhem.106/
  29. FrgMstr

    AI LLM hardware discussion thread

    No.
  30. FrgMstr

    AI LLM hardware discussion thread

    Not sure about that, but would be a nice setup for the memory footprint. I run models on my 7900XTX (24GB), and it is super speedy. 16GB would be somewhat limiting.
  31. FrgMstr

    Get it before its gone.... Local.AI

    Needed an account for off-label usage. The ideas behind the site are solid, it will be interesting to see how they pool data. Going to be messy at best, but should help with some insights.
  32. FrgMstr

    What LLM/Model you using?

    Meta/muse-glimmer 30B Kquant - That generally means it is somewhat dynamic in terms of quantization. But overall it seems to be a 4quant from scuttlebutt.
  33. FrgMstr

    Get it before its gone.... Local.AI

    Will be interesting to see how this fleshes out.
  34. FrgMstr

    What LLM/Model you using?

    On topic please.
  35. FrgMstr

    Get it before its gone.... Local.AI

    Linkage to grab your own. No downside that I can see.
  36. FrgMstr

    What LLM/Model you using?

    Muse has been disappointing me. Gave it a fairly large task building an RPG game. Hit a wall, beat on it for seven hours or so....no bueno. Swapped Laguna back in, fixing stuff left and right on the first prompts.
  37. FrgMstr

    What LLM/Model you using?

    Giving this a run and just playing around with some very long /goal prompts. meta/muse-glimmer Not exactly a speed machine...
  38. FrgMstr

    GPU prices — is the worst behind us ?

    I think the technical term you are looking for is, "FUBAR."
  39. FrgMstr

    GPU prices — is the worst behind us ?

    Things are going to get worse, before they get worser.
  40. FrgMstr

    Hello all!

    Off topic starts here: https://hardforum.com/forums/general-mayhem.106/ Enjoy!
Back
Top