GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

Justbackup/phi-4-abliterated-GGUF overview

About < quantize version: 2 < output tensor quantised: 1 < convert type: hf < vocab type: < tags: static quants of https://huggingface.co/huihui ai/phi 4 ablit…

transformersggufphinlpmathcodechatconversationalabliterateduncensoredenlicense:mitendpoints_compatibleregion:us

Runs locally from ~5.17 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline

Repository Files & Downloads

11 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
phi-4-abliterated.IQ4_XS.ggufGGUFGGUF7.46 GBDownload
phi-4-abliterated.Q2_K.ggufGGUFGGUF5.17 GBDownload
phi-4-abliterated.Q3_K_L.ggufGGUFGGUF7.39 GBDownload
phi-4-abliterated.Q3_K_M.ggufGGUFGGUF6.86 GBDownload
phi-4-abliterated.Q3_K_S.ggufGGUFGGUF6.06 GBDownload
phi-4-abliterated.Q4_K_M.ggufGGUFGGUF8.43 GBDownload
phi-4-abliterated.Q4_K_S.ggufGGUFGGUF7.86 GBDownload
phi-4-abliterated.Q5_K_M.ggufGGUFGGUF9.88 GBDownload
phi-4-abliterated.Q5_K_S.ggufGGUFGGUF9.45 GBDownload
phi-4-abliterated.Q6_K.ggufGGUFGGUF11.20 GBDownload
phi-4-abliterated.Q8_0.ggufGGUFGGUF14.51 GBDownload

Model Details

Model IDJustbackup/phi-4-abliterated-GGUF
AuthorJustbackup
Pipeline
Licensemit
Base modelhuihui-ai/phi-4-abliterated
Last modified2026-08-18T16:18:43.000Z

Model README

---

base_model: huihui-ai/phi-4-abliterated

language:

  • en

library_name: transformers

license: mit

license_link: https://huggingface.co/huihui-ai/phi-4-abliterated/resolve/main/LICENSE

quantized_by: mradermacher

tags:

  • phi
  • nlp
  • math
  • code
  • chat
  • conversational
  • abliterated
  • uncensored

---

About

<!-- ### quantize_version: 2 -->

<!-- ### output_tensor_quantised: 1 -->

<!-- ### convert_type: hf -->

<!-- ### vocab_type: -->

<!-- ### tags: -->

static quants of https://huggingface.co/huihui-ai/phi-4-abliterated

<!-- provided-files -->

weighted/imatrix quants are available at https://huggingface.co/mradermacher/phi-4-abliterated-i1-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of [TheBloke's

READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for

more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

| Link | Type | Size/GB | Notes |

|:-----|:-----|--------:|:------|

| GGUF | Q2_K | 5.6 | |

| GGUF | Q3_K_S | 6.6 | |

| GGUF | Q3_K_M | 7.5 | lower quality |

| GGUF | Q3_K_L | 8.0 | |

| GGUF | IQ4_XS | 8.1 | |

| GGUF | Q4_K_S | 8.5 | fast, recommended |

| GGUF | Q4_K_M | 9.2 | fast, recommended |

| GGUF | Q5_K_S | 10.3 | |

| GGUF | Q5_K_M | 10.7 | |

| GGUF | Q6_K | 12.1 | very good quality |

| GGUF | Q8_0 | 15.7 | fast, best quality |

Here is a handy graph by ikawrakow comparing some lower-quality quant

types (lower is better):

!image.png

And here are Artefact2's thoughts on the matter:

https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to

questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting

me use its servers and providing upgrades to my workstation to enable

this work in my free time.

<!-- end -->

Run Justbackup/phi-4-abliterated-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models