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

afrideva/llama2_xs_460M_uncensored-GGUF

afrideva Llama GGUF second-order 1K 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%2Fllama2_xs_460M_uncensored-GGUF"
Response includes
  • classification m-uncensored
  • files 9
  • hub_downloads_all_time 5,676
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=afrideva
All 3 models by afrideva
 GET/models?family=llama&method=m-uncensored
Sibling llama 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
6K
313 last 30d - cooling
Likes
1
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
Now5.8K→from436↑1,231%
02.1K4.3K6.4K436 on Jul 24, 20245.8K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 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.

haramberesearch/llama2_xs_460M_uncensored↓ 19 this lineage
afrideva/llama2_xs_460M_uncensored-GGUF↓ 313

Metadata

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 base_model:haramberesearch/llama2_xs_460M_uncensored

Related

Other by afrideva
kappa-3-phi-abliterated-GGUF 845 phi-2-uncensored-GGUF 670
Total size
2.67 GB
Files
9
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2023-12-21 04:13
Source huggingface.co/afrideva/llama2_xs_460M_uncensored-GGUF ↗ Base model haramberesearch/llama2_xs_460M_uncensored →

Files by quantization

F16 1 file 883 MB
llama2_xs_460m_uncensored.fp16.gguf 883 MB 4481be47 download
Auxiliary files 8 files 1.81 GB
llama2_xs_460m_uncensored.q8_0.gguf 470 MB 82466e72 download
llama2_xs_460m_uncensored.q6_k.gguf 363 MB bafeb790 download
llama2_xs_460m_uncensored.q5_k_m.gguf 318 MB a742c430 download
llama2_xs_460m_uncensored.q4_k_m.gguf 275 MB f866b951 download
llama2_xs_460m_uncensored.q3_k_m.gguf 228 MB ad6a2853 download
llama2_xs_460m_uncensored.q2_k.gguf 203 MB e003df0d download
README.md 2.77 KB b140c367 download
.gitattributes 1.98 KB 666d9edc download

README current version from Hugging Face

base_model: haramberesearch/llama2_xs_460M_uncensored
datasets:

  • unalignment/toxic-dpo-v0.1
    inference: false
    model_creator: haramberesearch
    model_name: llama2_xs_460M_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

haramberesearch/llama2_xs_460M_uncensored-GGUF

Quantized GGUF model files for llama2_xs_460M_uncensored from haramberesearch

Name Quant method Size
llama2_xs_460m_uncensored.fp16.gguf fp16 925.45 MB
llama2_xs_460m_uncensored.q2_k.gguf q2_k 212.56 MB
llama2_xs_460m_uncensored.q3_k_m.gguf q3_k_m 238.87 MB
llama2_xs_460m_uncensored.q4_k_m.gguf q4_k_m 288.52 MB
llama2_xs_460m_uncensored.q5_k_m.gguf q5_k_m 333.29 MB
llama2_xs_460m_uncensored.q6_k.gguf q6_k 380.87 MB
llama2_xs_460m_uncensored.q8_0.gguf q8_0 492.67 MB

Original Model Card:

llama2_xs_460M_uncensored

Model Details

llama2_xs_460M_experimental DPO finedtuned to remove alignment (3 epochs QLoRa).

Model Description

Out-of-Scope Use

Don't use this to do bad things. Bad things are bad.

Recommendations

Users (both direct and downstream) should be aware of the risks, biases and limitations of the model.

How to Get Started with the Model

https://github.com/oobabooga/text-generation-webui

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_hub1fb3d922.8 KB
    Loading...
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