Fuck AI

Yeah that's annoying. There are often ways to trick them into answering anyway, but if you want to avoid the fuss and frustration, find some heretic/abliterated/uncensored models on huggingface and run them in ollama and you can just straight up ask them whatever you want.

ollama run hf.co/mradermacher/Qwen3-4B-2507-Thinking-heretic-abliterated-uncensored-i1-GGUF:Q4_K_M is a small fast thinking model (2.5GB) that I've used a lot and has worked pretty well for me. Loads fast, runs on most hardware easily, thinks carefully about what you're asking (which can help you to clarify anything it's getting confused about) but still gives actual answers quickly.

If you're trying to squeeze a lot of information into an 8GB VRAM card, ollama run hf.co/mradermacher/Ministral-3-14B-abliterated-i1-GGUF:IQ3_M is a particularly knowledge-dense 6.2GB model and should leave some room for a decent bit of context and other VRAM usage without offloading too much. Ministral tends to love spitting out heavily formatted text (bold, italics, headings, tables) unless you very carefully convince it not to, so I find this one a bit obnoxious personally but it has good information in it and it looks nice if you're into that, I guess.

ollama run hf.co/noctrex/Llama-3.3-8B-Instruct-128k-abliterated-GGUF:Q8_0 is a good larger size (8.5GB) option that I use a lot, without thinking it just goes straight to the answer and it gives good, reliable results and it supports lots of context (you'll need to add an environment variable to ollama to use more than 4096 default context, and more context uses more VRAM). I like Llama models a lot.

If you've got plenty of VRAM (or don't mind that it will run much slower by offloading to system RAM) ollama run hf.co/mradermacher/Harbinger-24B-biprojected-norm-preserving-abliterated-i1-GGUF:Q4_K_M is a 14GB model I stumbled across that is supposed to be for writing stories and roleplaying, but it continues to impress me with its reliability, straightforward instruction following and broad knowledge base for general purpose tasks.

Good luck! It seems like it sometimes takes awhile for people to figure out effective ways to abliterate the latest models (which are also supposedly getting more sophisticated in their safety rules), so most of these abliterated models tend to be a little older from what I've found. And shoutout to mradermacher, whoever you are, who takes all these various models and makes quantized imatrix GGUF versions of them so we can easily run them efficiently on consumer hardware. I presume they are a lovely fellow!