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?

I also recommend gemma4 or qwen3.5. Both super solid in my experience for how lightweight they are

I suggest looking at llm arena leaderboards filtered by open weight models. It offers benchmarks at a very complete and statistically detailed level for models, and usually is quite up to date when new models come out. The new Gemma that just came out might be the best for 1x GPU, and if you have a bunch of vram check out the larger Chinese models

I'd say Qwen 3.5 and Gemma 4 beat GPT OSS in every aspect.

I'm not on there, but you might have more luck in !localllama@sh.itjust.works

You might also want to list the hardware that you plan to use, since that'll constrain what you can reasonably run.

Gemma4 e4b quant8 will fit in 12gb and is good

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.

Qwen is pretty good. Also try LFM models.

Just curious, what does "some automation" entail? I thought LLMs could only work with text, like summarize documents and that sort of thing.

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

What are your computer specs?

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

How much VRAM?

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.