CUSTOM
CLANKERS.
← Browse all models

AtomicChat / Model details

DeepSeek-V4.1-Flash-1017-Uncensored-GGUF

AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF

uncensoredfine-tuned
Download files on Hugging Face ↗

Read the original model card ↗ · Choosing a model

About this model

AtomicChat’s DeepSeek-V4.1-Flash-1017-Uncensored-GGUF is a derivative of deepseek-ai/DeepSeek-V4.1-Flash-1017 that projects DeepSeek’s refusal direction out of the released weights and bakes the edit into GGUF builds. The repository provides 2.67bpw-IQ1_M and 3.58bpw-Q2_K builds, plus a rank-1 GGUF LoRA adapter expressing the same residual-stream edit for compatible GGUF bases. According to the model card, the creator measured the files against Unsloth builds of matching layout and reports reduced refusals, while warning that IQ1_M reduced MMLU and showed more looping than the Q2_K build. The creator also says the edit removes refusals broadly rather than preserving a narrow topic set, and that long thinking traces may continue when the base model would have declined. These files require a llama.cpp build with DeepSeek-V4.1 support, which the card says was not yet in a release or Atomic Chat. The listed weight format is GGUF, and the repository license is MIT.

Description sources

Source-based description, not an independent evaluation. Check the linked sources for the creator’s claims and limitations.

Size and formats

Base model
deepseek-ai/DeepSeek-V4.1-Flash-1017
Parameters
Unknown
Main repository formats
GGUF
License tag
mit
Languages
Unknown
Last updated
2026-10-20 · 16:54:11.000 UTC

What changed

Model types are creator-reported, not independently tested. These labels describe source metadata, not a guarantee of behavior.

  • uncensoredmodel name: DeepSeek-V4.1-Flash-1017-Uncensored-GGUF
  • fine-tunedsource tag: base_model:finetune:deepseek-ai/DeepSeek-V4.1-Flash-1017

Family evidence

These groupings are source-reported. Explicit base identifiers take priority over generic architecture tags.

  • DeepSeek: Base model: deepseek-ai/DeepSeek-V4.1-Flash-1017

Available versions

Versions appear here only when they explicitly name this exact model as their source. Check each repository for available files.

Refusal profile

Not yet measured: no GGUF version is available for our runner.

How we measure

Link to this listing

Made or quantized this model? Paste one of these into your model card or README so people can find this listing.

Markdown

[Listed on Custom Clankers](https://customclankers.com/models/atomicchat-deepseek-v4-1-flash-1017-uncensored-gguf/)

HTML

<a href="https://customclankers.com/models/atomicchat-deepseek-v4-1-flash-1017-uncensored-gguf/">Listed on Custom Clankers</a>

Plain text links only: no image, no script, nothing loaded from this site.

Customize or build on this model

Listed from public GitHub data, not tested by us. Read the code and license before you run anything.

Tools to customize it further

Make a smaller download (quantize)

  • llama.cpp ↗ ★ 132,260

    Runs models locally and includes the tools behind most GGUF files. A conversion script turns Hugging Face weights into GGUF, and llama-quantize shrinks a high-precision GGUF to lower-bit formats, which can cost some accuracy.

Learn the techniques

  • LLM Course ↗ ★ 84,667

    A free course with roadmaps and Colab notebooks. Its notebooks include one-click tools for merging with MergeKit, quantizing to GGUF, GPTQ, EXL2, AWQ and HQQ, and automatic abliteration with custom datasets.

Compare all tools →

Source provenance

Downloads
752
Likes
35
Metadata checked
2026-10-24 · 09:40:11 UTC
First seen in index
2026-10-24 · 04:11:48 UTC
Source revision
f492d41e34953b8d292def32460adf08ef2e4d71

Source-card excerpt

Source model card excerpt: How to Run DeepSeek-V4.1-Flash-1017 Without Refusals Locally DeepSeek's refusal direction projected out of the released weights, baked into GGUF builds and measured against the

From AtomicChat/DeepSeek-V4.1-Flash-1017-Uncensored-GGUF. Creator model-card excerpt, not an independent review.

Inspect before you run

Low refusal is not proof of correctness. Outputs can be inaccurate, harmful, or biased. Review the model card, license and files yourself. A license tag is not commercial-use advice. Parameter counts are source metadata; no hardware compatibility is implied.

This directory does not host or redistribute model weights. Refusal profiles are measured by us on a fixed prompt set; all other behavior claims are source-reported.

Collection rules & limitations ↗