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

second-state/Wizard-Vicuna-13B-Uncensored-GGUF

second-state Llama 13B 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/second-state%2FWizard-Vicuna-13B-Uncensored-GGUF"
Response includes
  • classification m-uncensored
  • files 15
  • hub_downloads_all_time 50,335
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=second-state
All 3 models by second-state
 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
50K
3K last 30d - cooling
Likes
16
Model age
3.0y ago
created 2023-10-26

Training 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.

ehartford/wizard_vicuna_70k_unfiltered
Downloads over time
Now51.7K→from1.4K↑3,511%
018.9K37.8K56.7K1.4K on Jul 24, 202451.7K on Oct 12Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 12 · 162 snapshots · spans 810 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.

ehartford/Wizard-Vicuna-13B-Uncensored this lineage
second-state/Wizard-Vicuna-13B-Uncensored-GGUF↓ 3,439

Metadata

License
other
Languages
en
Quantizations
Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0
Tags
transformers gguf llama text-generation uncensored en dataset:ehartford/wizard_vicuna_70k_unfiltered base_model:QuixiAI/Wizard-Vicuna-13B-Uncensored base_model:quantized:QuixiAI/Wizard-Vicuna-13B-Uncensored license:other region:us

Related

Other by second-state
Llama-3.2-3B-Instruct-Uncensored-GGUF 606 WizardLM-13B-V1.0-Uncensored-GGUF 595
Same base model
TheBloke/Wizard-Vicuna-13B-Uncensored-GGUF 12K TheBloke/Wizard-Vicuna-13B-Uncensored-GPTQ 134 Iambackup/Wizard-Vicuna-13B-Uncensored-GGUF 80 TheBloke/Wizard-Vicuna-13B-Uncensored-AWQ 43
Total size
91.4 GB
Files
15
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2024-03-20 07:19
Source huggingface.co/second-state/Wizard-Vicuna-13B-Uncensored-GGUF ↗ Base model ehartford/Wizard-Vicuna-13B-Uncensored ↗

Files by quantization

Q8_0 1 file 12.9 GB
Wizard-Vicuna-13B-Uncensored-Q8_0.gguf 12.9 GB 0cdd5a68 download
Q6_K 1 file 9.95 GB
Wizard-Vicuna-13B-Uncensored-Q6_K.gguf 9.95 GB 72f7855f download
Q5_K 2 files 17.0 GB
Wizard-Vicuna-13B-Uncensored-Q5_K_M.gguf 8.60 GB bb6bda4e download
Wizard-Vicuna-13B-Uncensored-Q5_K_S.gguf 8.36 GB 24e1411d download
Q5 1 file 8.36 GB
Wizard-Vicuna-13B-Uncensored-Q5_0.gguf 8.36 GB bd2d14bc download
Q4_K 2 files 14.2 GB
Wizard-Vicuna-13B-Uncensored-Q4_K_M.gguf 7.33 GB 07e741ce download
Wizard-Vicuna-13B-Uncensored-Q4_K_S.gguf 6.91 GB 4620866b download
Q4 1 file 6.86 GB
Wizard-Vicuna-13B-Uncensored-Q4_0.gguf 6.86 GB 4266f002 download
Q3_K 3 files 17.6 GB
Wizard-Vicuna-13B-Uncensored-Q3_K_L.gguf 6.45 GB 9fc112b7 download
Wizard-Vicuna-13B-Uncensored-Q3_K_M.gguf 5.90 GB e1d9f083 download
Wizard-Vicuna-13B-Uncensored-Q3_K_S.gguf 5.27 GB caffcb13 download
Q2_K 1 file 4.52 GB
Wizard-Vicuna-13B-Uncensored-Q2_K.gguf 4.52 GB d087713b download
Auxiliary files 3 files 6.45 KB
README.md 4.35 KB 27bbba40 download
.gitattributes 1.53 KB f15b49c2 download
config.json 583 B 720d6221 download

README current version from Hugging Face

base_model: ehartford/Wizard-Vicuna-13B-Uncensored
inference: false
library_name: transformers
license: other
model_creator: Eric Hartford
model_name: Wizard Vicuna 13B Uncensored
model_type: llama
pipeline_tag: text-generation
quantized_by: Second State Inc.
language:

  • en
    tags:
  • uncensored
    datasets:
  • ehartford/wizard_vicuna_70k_unfiltered

Wizard-Vicuna-13B-Uncensored-GGUF

Original Model

cognitivecomputations/Wizard-Vicuna-13B-Uncensored

Run with LlamaEdge

  • LlamaEdge version: v0.2.8 and above

  • Prompt template

    • Prompt type: vicuna-1.0-chat

    • Prompt string

      {system} USER: {prompt} ASSISTANT:

  • Context size: 5120

  • Run as LlamaEdge service

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Wizard-Vicuna-13B-Uncensored-Q5_K_M.gguf llama-api-server.wasm -p vicuna-1.0-chat

  • Run as LlamaEdge command app

    wasmedge --dir .:. --nn-preload default:GGML:AUTO:Wizard-Vicuna-13B-Uncensored-Q5_K_M.gguf llama-chat.wasm -p vicuna-1.0-chat

Quantized GGUF Models

Name Quant method Bits Size Use case
Wizard-Vicuna-13B-Uncensored-Q2_K.gguf Q2_K 2 4.85 GB smallest, significant quality loss - not recommended for most purposes
Wizard-Vicuna-13B-Uncensored-Q3_K_L.gguf Q3_K_L 3 6.93 GB small, substantial quality loss
Wizard-Vicuna-13B-Uncensored-Q3_K_M.gguf Q3_K_M 3 6.34 GB very small, high quality loss
Wizard-Vicuna-13B-Uncensored-Q3_K_S.gguf Q3_K_S 3 5.66 GB very small, high quality loss
Wizard-Vicuna-13B-Uncensored-Q4_0.gguf Q4_0 4 7.37 GB legacy; small, very high quality loss - prefer using Q3_K_M
Wizard-Vicuna-13B-Uncensored-Q4_K_M.gguf Q4_K_M 4 7.87 GB medium, balanced quality - recommended
Wizard-Vicuna-13B-Uncensored-Q4_K_S.gguf Q4_K_S 4 7.42 GB small, greater quality loss
Wizard-Vicuna-13B-Uncensored-Q5_0.gguf Q5_0 5 8.97 GB legacy; medium, balanced quality - prefer using Q4_K_M
Wizard-Vicuna-13B-Uncensored-Q5_K_M.gguf Q5_K_M 5 9.23 GB large, very low quality loss - recommended
Wizard-Vicuna-13B-Uncensored-Q5_K_S.gguf Q5_K_S 5 8.97 GB large, low quality loss - recommended
Wizard-Vicuna-13B-Uncensored-Q6_K.gguf Q6_K 6 10.7 GB very large, extremely low quality loss
Wizard-Vicuna-13B-Uncensored-Q8_0.gguf Q8_0 8 13.8 GB very large, extremely low quality loss - not recommended

README history 9 versions

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

  1. 2024-03-20Update README.mdda528bb4.4 KB
    Loading...
  2. 2024-02-25Update README.mdc62622f4.3 KB
    Loading...
  3. 2024-02-24Update README.mdfd348c34.3 KB
    Loading...
  4. 2024-01-28Update README.md413a54b4.3 KB
    Loading...
  5. 2024-01-26Update README.mddd001f64.3 KB
    Loading...
  6. 2024-01-26Update README.mde62b6684.3 KB
    Loading...
  7. 2024-01-16Update852077c4.3 KB
    Loading...
  8. 2023-10-26Add `wizard-vicuna-13b-ggml-model-q8_0.gguf`0f01de3242 B
    Loading...
  9. 2023-10-26initial commitcb2dae628 B
    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