DeepSeek-v4.1-Flash-1017

DeepSeek V4.1 Flash 1017 was recently released, and a user has provided an "abliterated" version along with GGUF quants for both the base and abliterated models. The abliterated model significantly reduces refusals, with only 4 out of 100 prompts refused compared to 97 out of 100 in the original V4.1. In 'think mode,' refusals dropped from 98/100 to 9/100. All models and a LoRA for GGUFs are available on the Hub.

This model is a specific October 17, 2026 snapshot of DeepSeek V4.1 Flash, unlike other versions that may not specify the exact date of the snapshot.