Hey :) For a while now I use gpt-oss-20b on my home lab for lightweight coding tasks and some automation. I’m not so up to date with the current self-hosted LLMs and since the model I’m using was released at the beginning of August 2025 (From an LLM development perspective, it feels like an eternity to me) I just wanted to use the collective wisdom of lemmy to maybe replace my model with something better out there.

Edit:

Specs:

GPU: RTX 3060 (12GB vRAM)

RAM: 64 GB

gpt-oss-20b does not fit into the vRAM completely but it partially offloaded and is reasonably fast (enough for me)

  • Jozzo@lemmy.worldEnglish
    241·
    20 days ago

    I find Qwen3.5 is the best at toolcalling and agent use, otherwise Gemma4 is a very solid all-rounder and it should be the first you try. Tbh gpt-oss is still good to this day, are you running into any problems w it?

    • Tanka@lemmy.mlOPEnglish
      41·
      20 days ago

      No problems per se. I just thought that I had not checked for an update for a longer time.

      • jacksilver@lemmy.worldEnglish
        2·
        19 days ago

        You’re probably aware, but updating the model periodically is probably a good idea just because things do change overtime.

        A model from two years ago was trained on data from at least two years ago. Meaning any technology, code, world event changes wouldn’t be reflected in the model.

  • carzian@lemmy.mlEnglish
    41·
    20 days ago

    I’m in the same boat. You’ll get better responses if you post your machine specs. I

  • cron@feddit.orgEnglish
    41·
    20 days ago

    The latest open weights model from google might be a good fit for you. The 26B model works pretty well on my machine, though the performance isn’t great (6 tokens per second, CPU only).

  • SuspciousCarrot78@lemmy.worldEnglish
    2·
    19 days ago

    What sort of coding and what sort of automation tasks? The latter is an easier ticket to fill than the former, though I might have an idea for you on that end if coding is a must

  • jaschen306@sh.itjust.worksEnglish
    2·
    20 days ago

    I’m running gemma4 26b MOE for most of my agent calls. I use glm5:cloud for my development agent because 26b struggles when the context windows gets too big.

  • Evotech@lemmy.worldEnglish
    31·
    18 days ago

    I’d use some Chinese model. Qwen3.5 Claude 4.6 distilled ablitirated is what I use