← Local AI Release Board

OBLITERATUS/DeepSeek-V4.1-Flash-1017-obliterated

just landed · new, unvettedmodel

New, unvetted: created or first seen in the last few days, not from a trusted org and not past the signal threshold yet.

DeepSeek-V4.1-Flash-1017-obliterated is a refusal-direction ablated version of DeepSeek-V4.1-Flash-1017, produced with OBLITERATUS using the failspy method. Mixture-of-experts, 755B total (384 experts, 6 per token). Context: 1M tokens (config). License: mit.

Org
OBLITERATUS
Released
2026-10-23
Status
just landed · new, unvetted
License
mit (permissive)
Parameters
754.6B
Architecture
MoE · 384 experts, 6/token · DeepseekV41ForCausalLM
Context
1,048,576 tokens
Task
text-generation · text
Signal
2 HF likes · 44 downloads

Runs on

mixed: real files + estimate; need = weights + FP16 KV cache for 8K tokens + 1GB. A sizing calculation, not tested.

Links

First published here 2026-10-23 · updated 2026-10-29 · markdown · JSON