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

RichardErkhov/Fredithefish_-_Guanaco-3B-Uncensored-gguf

RichardErkhov 3B GGUF 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/RichardErkhov%2FFredithefish_-_Guanaco-3B-Uncensored-gguf"
Response includes
  • classification m8
  • files 24
  • hub_downloads_all_time 3,997
  • author_summary 257 models
  • readme_text full
Try next
GET/models?author=RichardErkhov
All 257 models by RichardErkhov
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 2 signals
Method inferred from partial signals - repository name, related files, or tag patterns. Producer identity not confirmed; label may sharpen or shift as we gather more evidence.
  • author=richarderkhov (M8 quantization producer)
  • is_gguf=1
How we label → About M8 →
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
4K
490 last 30d - stable
Likes
1
Model age
2.2y ago
created 2024-07-30
Downloads over time
Now4.1K→from264↑1,467%
01.5K3K4.5K264 on Jul 31, 20244.1K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 31, 2024 → Oct 11 · 154 snapshots · spans 802 days

Variants by this author 2 formats · 498 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Quantizations
IQ3 IQ4 Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0
Tags
gguf endpoints_compatible region:us

Related

Other by RichardErkhov
byroneverson_-_gemma-2-27b-it-abliterated-gguf 2K huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-gguf 2K failspy_-_Codestral-22B-v0.1-abliterated-v3-gguf 2K Rupesh2_-_Llama-3.1-8B-Uncensored-gguf 2K huihui-ai_-_Qwen2.5-32B-Instruct-abliterated-gguf 2K
Total size
35.2 GB
Files
24
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2024-07-30 16:43
Source huggingface.co/RichardErkhov/Fredithefish_-_Guanaco-3B-Uncensored-gguf ↗

Files by quantization

Q8_0 1 file 2.75 GB
Guanaco-3B-Uncensored.Q8_0.gguf 2.75 GB 20076d36 download
Q6_K 1 file 2.13 GB
Guanaco-3B-Uncensored.Q6_K.gguf 2.13 GB a986840a download
Q5 2 files 3.75 GB
Guanaco-3B-Uncensored.Q5_1.gguf 1.95 GB 8f0a7cdb download
Guanaco-3B-Uncensored.Q5_0.gguf 1.80 GB 90d98f14 download
Q5_K 3 files 5.65 GB
Guanaco-3B-Uncensored.Q5_K.gguf 1.93 GB 28dbff2b download
Guanaco-3B-Uncensored.Q5_K_M.gguf 1.93 GB 28dbff2b download
Guanaco-3B-Uncensored.Q5_K_S.gguf 1.80 GB 17f7b7b5 download
Q4_K 3 files 4.83 GB
Guanaco-3B-Uncensored.Q4_K.gguf 1.66 GB bc3f2009 download
Guanaco-3B-Uncensored.Q4_K_M.gguf 1.66 GB bc3f2009 download
Guanaco-3B-Uncensored.Q4_K_S.gguf 1.50 GB 23b868b6 download
Q4 2 files 3.13 GB
Guanaco-3B-Uncensored.Q4_1.gguf 1.64 GB 971f4c4b download
Guanaco-3B-Uncensored.Q4_0.gguf 1.49 GB 6eadd27a download
IQ4 2 files 2.93 GB
Guanaco-3B-Uncensored.IQ4_NL.gguf 1.50 GB d20cd622 download
Guanaco-3B-Uncensored.IQ4_XS.gguf 1.43 GB c6fd2329 download
Q3_K 4 files 5.41 GB
Guanaco-3B-Uncensored.Q3_K_L.gguf 1.49 GB 2d4ffe03 download
Guanaco-3B-Uncensored.Q3_K.gguf 1.38 GB 319f218d download
Guanaco-3B-Uncensored.Q3_K_M.gguf 1.38 GB 319f218d download
Guanaco-3B-Uncensored.Q3_K_S.gguf 1.16 GB 06b03ad5 download
IQ3 3 files 3.58 GB
Guanaco-3B-Uncensored.IQ3_M.gguf 1.28 GB 7ac27f32 download
Guanaco-3B-Uncensored.IQ3_S.gguf 1.16 GB 79a62ddb download
Guanaco-3B-Uncensored.IQ3_XS.gguf 1.14 GB a1bf5322 download
Q2_K 1 file 1.01 GB
Guanaco-3B-Uncensored.Q2_K.gguf 1.01 GB c1df60c6 download
Auxiliary files 2 files 8.51 KB
README.md 5.55 KB 4acb2611 download
.gitattributes 2.97 KB fcc0f950 download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Guanaco-3B-Uncensored - GGUF

Name Quant method Size
Guanaco-3B-Uncensored.Q2_K.gguf Q2_K 1.01GB
Guanaco-3B-Uncensored.IQ3_XS.gguf IQ3_XS 1.14GB
Guanaco-3B-Uncensored.IQ3_S.gguf IQ3_S 1.16GB
Guanaco-3B-Uncensored.Q3_K_S.gguf Q3_K_S 1.16GB
Guanaco-3B-Uncensored.IQ3_M.gguf IQ3_M 1.28GB
Guanaco-3B-Uncensored.Q3_K.gguf Q3_K 1.38GB
Guanaco-3B-Uncensored.Q3_K_M.gguf Q3_K_M 1.38GB
Guanaco-3B-Uncensored.Q3_K_L.gguf Q3_K_L 1.49GB
Guanaco-3B-Uncensored.IQ4_XS.gguf IQ4_XS 1.43GB
Guanaco-3B-Uncensored.Q4_0.gguf Q4_0 1.49GB
Guanaco-3B-Uncensored.IQ4_NL.gguf IQ4_NL 1.5GB
Guanaco-3B-Uncensored.Q4_K_S.gguf Q4_K_S 1.5GB
Guanaco-3B-Uncensored.Q4_K.gguf Q4_K 1.66GB
Guanaco-3B-Uncensored.Q4_K_M.gguf Q4_K_M 1.66GB
Guanaco-3B-Uncensored.Q4_1.gguf Q4_1 1.64GB
Guanaco-3B-Uncensored.Q5_0.gguf Q5_0 1.8GB
Guanaco-3B-Uncensored.Q5_K_S.gguf Q5_K_S 1.8GB
Guanaco-3B-Uncensored.Q5_K.gguf Q5_K 1.93GB
Guanaco-3B-Uncensored.Q5_K_M.gguf Q5_K_M 1.93GB
Guanaco-3B-Uncensored.Q5_1.gguf Q5_1 1.95GB
Guanaco-3B-Uncensored.Q6_K.gguf Q6_K 2.13GB
Guanaco-3B-Uncensored.Q8_0.gguf Q8_0 2.75GB

Original model description:

license: apache-2.0
datasets:

  • Fredithefish/openassistant-guanaco-unfiltered
    language:
  • en
    library_name: transformers
    pipeline_tag: conversational
    inference: false
Alt Text

✨ Guanaco - 3B - Uncensored ✨

IMPORTANT:

This is the old model. The dataset has been updated and a newer version of this model is available here.


Guanaco-3B-Uncensored has been fine-tuned for 6 epochs on the Unfiltered Guanaco Dataset. using RedPajama-INCITE-Base-3B-v1 as the base model.

The model does not perform well with languages other than English.

Please note: This model is designed to provide responses without content filtering or censorship. It generates answers without denials.

Special thanks

I would like to thank AutoMeta for providing me with the computing power necessary to train this model.

Prompt Template

### Human: {prompt} ### Assistant:

README history 1 version

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

  1. 2024-07-30uploaded readme6fb62885.5 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