Get the app
← back to catalog · registered 2026-08-22 13:56

afrideva/phi-2-uncensored-GGUF

afrideva Phi GGUF second-order 2K ctx
Your rig guess connected
? Why do I need an app?
Reading your rig…

This is a rough estimate. Install the free app - we'll show exact numbers.

Reading real hardware from your app right now. Numbers below are exact.

Below is the per-quantization compatibility for this model. 

curl -H "Authorization: Bearer $ABL_KEY" \
     "https://abliteration.org/api/v1/models/afrideva%2Fphi-2-uncensored-GGUF"
Response includes
  • classification m-uncensored
  • files 9
  • hub_downloads_all_time 35,924
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=afrideva
All 3 models by afrideva
 GET/models?family=phi&method=m-uncensored
Sibling phi models · same method
 GET/methods/m-uncensored
What "m-uncensored" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M-U
Primary method

Uncensored (method unknown)

No other method signals detected in this model.
Confidence
LOW
Why this label 3 signals
Weak or ambiguous signals. Best guess based on catalog patterns; treat as tentative and check the evidence below.
  • 'uncensored' in name/tags but no 'abliterated' marker
  • method not identifiable from author declaration alone
  • may be DPO fine-tune, prompt engineering, or unknown technique
How we label → About M-U →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
36K
670 last 30d - cooling
Likes
14
Model age
2.8y ago
created 2023-12-21

Training datasets

1 of 1 in /datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

unalignment/toxic-dpo-v0.1 heal
Downloads over time
Now36.1K→from669↑5,303%
013.2K26.5K39.7K669 on Jul 24, 202436.1K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 158 snapshots · spans 809 days

Genealogy 0 direct forks

Full fork graph →

This model's place in the market. Above: what it was derived from. Below: the tree of everything derived from it.

Walmart-the-bag/phi-2-uncensored this lineage
afrideva/phi-2-uncensored-GGUF↓ 670

Metadata

License
other
Quantizations
F16
Tags
gguf ggml quantized q2_k q3_k_m q4_k_m q5_k_m q6_k q8_0 text-generation dataset:unalignment/toxic-dpo-v0.1 license:other

Related

Other by afrideva
kappa-3-phi-abliterated-GGUF 845 llama2_xs_460M_uncensored-GGUF 313
Total size
16.1 GB
Files
9
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2023-12-21 03:55
Source huggingface.co/afrideva/phi-2-uncensored-GGUF ↗ Base model Walmart-the-bag/phi-2-uncensored ↗

Files by quantization

F16 1 file 5.18 GB
phi-2-uncensored.fp16.gguf 5.18 GB 7e54461e download
Auxiliary files 8 files 11.0 GB
phi-2-uncensored.q8_0.gguf 2.75 GB 45d78b88 download
phi-2-uncensored.q6_k.gguf 2.13 GB ee34aad5 download
phi-2-uncensored.q5_k_m.gguf 1.93 GB b002e906 download
phi-2-uncensored.q4_k_m.gguf 1.67 GB dc19261f download
phi-2-uncensored.q3_k_m.gguf 1.38 GB 5186c2f8 download
phi-2-uncensored.q2_k.gguf 1.09 GB 6750df9e download
.gitattributes 1.92 KB 7e8ebf64 download
README.md 1.72 KB d1f12bfe download

README current version from Hugging Face

base_model: Walmart-the-bag/phi-2-uncensored
datasets:

  • unalignment/toxic-dpo-v0.1
    inference: false
    license: other
    license_link: https://huggingface.co/microsoft/phi-2/resolve/main/LICENSE
    license_name: microsoft-research-license
    model_creator: Walmart-the-bag
    model_name: phi-2-uncensored
    pipeline_tag: text-generation
    quantized_by: afrideva
    tags:
  • gguf
  • ggml
  • quantized
  • q2_k
  • q3_k_m
  • q4_k_m
  • q5_k_m
  • q6_k
  • q8_0

Walmart-the-bag/phi-2-uncensored-GGUF

Quantized GGUF model files for phi-2-uncensored from Walmart-the-bag

Name Quant method Size
phi-2-uncensored.fp16.gguf fp16 5.56 GB
phi-2-uncensored.q2_k.gguf q2_k 1.17 GB
phi-2-uncensored.q3_k_m.gguf q3_k_m 1.48 GB
phi-2-uncensored.q4_k_m.gguf q4_k_m 1.79 GB
phi-2-uncensored.q5_k_m.gguf q5_k_m 2.07 GB
phi-2-uncensored.q6_k.gguf q6_k 2.29 GB
phi-2-uncensored.q8_0.gguf q8_0 2.96 GB

Original Model Card:

README history 1 version

The author's README evolved over time. Click a version to see its content at that point.

  1. 2023-12-21Upload README.md with huggingface_hubc102d041.7 KB
    Loading...

Discussions 2 threads

  1. 2025-04-11What is it's chat format??open1 💬#2
    Loading...
  2. 2024-01-26Segmentation fault on kobold cpp 1.55.1 using phi-2-uncensored.q4_k_m.ggufopen1 💬#1
    Loading...

Continue on Hugging Face →

Catalog is the map. Apps are the tools.

Run models on your own machine, not in the cloud.

Every model page has an "Open in Abliteration" button that hands the model directly to the first-party desktop client, at the quantization your rig can actually run. No API keys, no subscription, no prompt leakage.

Get the app Browse the catalog
Open in Abliteration