12
submitted 4 months ago* (last edited 4 months ago) by venusaur@lemmy.world to c/fosai@lemmy.world

I downloaded an uncensored aggressive Qwen 3.5 model and I can see in its reasoning that it is still limiting responses based on safety guardrails (e.g. violence, NSFW).

Anybody have recommendations for truly uncensored models?

EDIT: I turned off reasoning and I think it’s more uncensored if I’m very specific about what the response should include.

you are viewing a single comment's thread
view the rest of the comments
[-] venusaur@lemmy.world 2 points 4 months ago

Jesus that MoE wiki is a fucking rabbit hole.

Thanks for sharing! Unfortunately I haven’t invested in a decent computer yet. Using 16GB GPU so been stuck on 4B Q4’s.

I’m not particularly interested in ERP, but I have obviously been using it for testing models. I’m more curious about other topics with guardrails.

I noticed that Qwen 3.5 uncensored is good if I turn off reasoning and explicitly say I want it to break the rules.

I’ll check out sillytavern tho. Thanks!

this post was submitted on 30 Apr 2026
12 points (80.0% liked)

Free Open-Source Artificial Intelligence

4816 readers
27 users here now

Welcome to Free Open-Source Artificial Intelligence!

We are a community dedicated to forwarding the availability and access to:

Free Open Source Artificial Intelligence (F.O.S.A.I.)

More AI Communities

LLM Leaderboards

Developer Resources

GitHub Projects

FOSAI Time Capsule

founded 3 years ago
MODERATORS