← All models
mlabonne

Qwen 3 Abliterated 1.7B

A reduced-refusal Qwen model adapted by mlabonne. Experimental; answer quality can differ from the original.

Offline PlusExperimentalConversation

About Qwen 3 Abliterated 1.7B

A community adaptation of Qwen 3 1.7B by mlabonne with refusal behaviour reduced. An experimental take on a small all-rounder; verify anything important it tells you.

Every model in this catalog runs locally in the Offline AI Chat app. After the download finishes, Qwen 3 Abliterated answers on your phone with no connection, and your prompts and replies are never uploaded.

Requirements & details

Download size
1.1 GB (Q4_K_M GGUF)
Memory needed
4.5 GB minimum · 6 GB recommended
Context in app
2,048 tokens
Runs on
Android 8+, 64-bit · iOS in private testing
Access
Offline Plus subscription
License
Apache-2.0