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)
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?
No problems per se. I just thought that I had not checked for an update for a longer time.
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.
I also recommend gemma4 or qwen3.5. Both super solid in my experience for how lightweight they are
Still can’t get my gemma to give me complete unbuggy components
I guess I have been using gemma4 fro more role playing games. Qwen3.5 seems to be better coder actually
I’d say Qwen 3.5 and Gemma 4 beat GPT OSS in every aspect.
Gemma4 e4b quant8 will fit in 12gb and is good
I’m in the same boat. You’ll get better responses if you post your machine specs. I
I’d use some Chinese model. Qwen3.5 Claude 4.6 distilled ablitirated is what I use
How much VRAM?
deleted by creator
Qwen is pretty good. Also try LFM models.
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.
Have you tried the new gemma4 models? The e4b fits in the 12gb memory and is pretty good. Or you can use 31b too, if you’re okay with offloading to CPU.
