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

RichardErkhov/brianmatzelle_-_llama3.2-3b-instruct-hasanpiker-abliterated-gguf

RichardErkhov Llama 3B GGUF 131K 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%2Fbrianmatzelle_-_llama3.2-3b-instruct-hasanpiker-abliterated-gguf"
Response includes
  • classification m8
  • files 24
  • hub_downloads_all_time 5,614
  • author_summary 257 models
  • readme_text full
Try next
GET/models?author=RichardErkhov
All 257 models by RichardErkhov
 GET/models?family=llama&method=m8
Sibling llama models · same method
 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
6K
587 last 30d - stable
Likes
0
Model age
18mo ago
created 2025-03-26
Downloads over time
Now5.8K→from409↑1,308%
1412.2K4.2K6.3K409 on Mar 26, 20255.8K on Oct 11Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 26, 2025 → Oct 11 · 120 snapshots · spans 564 days

Metadata

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

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
41.1 GB
Files
24
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2025-03-26 03:38
Source huggingface.co/RichardErkhov/brianmatzelle_-_llama3.2-3b-instruct-hasanpiker-abliterated-gguf ↗

Files by quantization

Q8_0 1 file 3.19 GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q8_0.gguf 3.19 GB 956e795c download
Q6_K 1 file 2.46 GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q6_K.gguf 2.46 GB aab24ab2 download
Q5 2 files 4.39 GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q5_1.gguf 2.28 GB f74d9cca download
llama3.2-3b-instruct-hasanpiker-abliterated.Q5_0.gguf 2.11 GB 24edd6fc download
Q5_K 3 files 6.44 GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q5_K.gguf 2.16 GB 9671e8a6 download
llama3.2-3b-instruct-hasanpiker-abliterated.Q5_K_M.gguf 2.16 GB 9671e8a6 download
llama3.2-3b-instruct-hasanpiker-abliterated.Q5_K_S.gguf 2.11 GB ba62d337 download
Q4 2 files 3.74 GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q4_1.gguf 1.95 GB 994c5081 download
llama3.2-3b-instruct-hasanpiker-abliterated.Q4_0.gguf 1.79 GB 1891eae4 download
Q4_K 3 files 5.56 GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q4_K.gguf 1.88 GB 982b2574 download
llama3.2-3b-instruct-hasanpiker-abliterated.Q4_K_M.gguf 1.88 GB 982b2574 download
llama3.2-3b-instruct-hasanpiker-abliterated.Q4_K_S.gguf 1.80 GB 0d4a5a85 download
IQ4 2 files 3.51 GB
llama3.2-3b-instruct-hasanpiker-abliterated.IQ4_NL.gguf 1.79 GB 88522dd6 download
llama3.2-3b-instruct-hasanpiker-abliterated.IQ4_XS.gguf 1.71 GB 96d8c085 download
Q3_K 4 files 6.27 GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q3_K_L.gguf 1.69 GB 2b32a9e4 download
llama3.2-3b-instruct-hasanpiker-abliterated.Q3_K.gguf 1.57 GB 0d9aed6b download
llama3.2-3b-instruct-hasanpiker-abliterated.Q3_K_M.gguf 1.57 GB 0d9aed6b download
llama3.2-3b-instruct-hasanpiker-abliterated.Q3_K_S.gguf 1.44 GB 3a89f90a download
IQ3 3 files 4.30 GB
llama3.2-3b-instruct-hasanpiker-abliterated.IQ3_M.gguf 1.49 GB 1fdecb4a download
llama3.2-3b-instruct-hasanpiker-abliterated.IQ3_S.gguf 1.44 GB 5b8a430c download
llama3.2-3b-instruct-hasanpiker-abliterated.IQ3_XS.gguf 1.38 GB 23060770 download
Q2_K 1 file 1.27 GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q2_K.gguf 1.27 GB 882a4c4f download
Auxiliary files 2 files 9.81 KB
README.md 6.37 KB e3af44b1 download
.gitattributes 3.44 KB ef9e7f9b download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama3.2-3b-instruct-hasanpiker-abliterated - GGUF

Name Quant method Size
llama3.2-3b-instruct-hasanpiker-abliterated.Q2_K.gguf Q2_K 1.27GB
llama3.2-3b-instruct-hasanpiker-abliterated.IQ3_XS.gguf IQ3_XS 1.38GB
llama3.2-3b-instruct-hasanpiker-abliterated.IQ3_S.gguf IQ3_S 1.44GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q3_K_S.gguf Q3_K_S 1.44GB
llama3.2-3b-instruct-hasanpiker-abliterated.IQ3_M.gguf IQ3_M 1.49GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q3_K.gguf Q3_K 1.57GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q3_K_M.gguf Q3_K_M 1.57GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q3_K_L.gguf Q3_K_L 1.69GB
llama3.2-3b-instruct-hasanpiker-abliterated.IQ4_XS.gguf IQ4_XS 1.71GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q4_0.gguf Q4_0 1.79GB
llama3.2-3b-instruct-hasanpiker-abliterated.IQ4_NL.gguf IQ4_NL 1.79GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q4_K_S.gguf Q4_K_S 1.8GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q4_K.gguf Q4_K 1.88GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q4_K_M.gguf Q4_K_M 1.88GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q4_1.gguf Q4_1 1.95GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q5_0.gguf Q5_0 2.11GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q5_K_S.gguf Q5_K_S 2.11GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q5_K.gguf Q5_K 2.16GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q5_K_M.gguf Q5_K_M 2.16GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q5_1.gguf Q5_1 2.28GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q6_K.gguf Q6_K 2.46GB
llama3.2-3b-instruct-hasanpiker-abliterated.Q8_0.gguf Q8_0 3.19GB

Original model description:

base_model: huihui-ai/Llama-3.2-3B-Instruct-abliterated
tags:

  • text-generation-inference
  • transformers
  • unsloth
  • llama
  • trl
  • sft
    license: apache-2.0
    language:
  • en

Uploaded model

  • Developed by: brianmatzelle
  • License: apache-2.0
  • Finetuned from model : huihui-ai/Llama-3.2-3B-Instruct-abliterated

This llama model was trained 2x faster with Unsloth and Huggingface's TRL library.

README history 1 version

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

  1. 2025-03-26uploaded readme9489df66.4 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