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

RichardErkhov/brianmatzelle_-_llama3.2-1b-instruct-hasanpiker-abliterated-gguf

RichardErkhov Llama 1B 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_-_llama3.2-1b-instruct-hasanpiker-abliterated-gguf"
Response includes
  • classification m8
  • files 24
  • hub_downloads_all_time 4,121
  • 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
4K
577 last 30d - stable
Likes
0
Model age
20mo ago
created 2025-02-14
Downloads over time
Now4.2K→from398↑966%
2061.7K3.2K4.6K398 on Feb 12, 20254.2K on Oct 11Feb '25May '25Aug '25Nov '25FebMayAug
Feb 12, 2025 → Oct 11 · 126 snapshots · spans 606 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
16.5 GB
Files
24
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2025-02-14 05:05
Source huggingface.co/RichardErkhov/brianmatzelle_-_llama3.2-1b-instruct-hasanpiker-abliterated-gguf ↗

Files by quantization

Q8_0 1 file 1.23 GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q8_0.gguf 1.23 GB f0c3897a download
Q6_K 1 file 974 MB
llama3.2-1b-instruct-hasanpiker-abliterated.Q6_K.gguf 974 MB d785ef95 download
Q5 2 files 1.72 GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q5_1.gguf 909 MB 952eff5e download
llama3.2-1b-instruct-hasanpiker-abliterated.Q5_0.gguf 851 MB d22dc57d download
Q5_K 3 files 2.53 GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q5_K.gguf 869 MB 33c52675 download
llama3.2-1b-instruct-hasanpiker-abliterated.Q5_K_M.gguf 869 MB 33c52675 download
llama3.2-1b-instruct-hasanpiker-abliterated.Q5_K_S.gguf 851 MB 990728ca download
Q4 2 files 1.49 GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q4_1.gguf 793 MB eecbb5af download
llama3.2-1b-instruct-hasanpiker-abliterated.Q4_0.gguf 735 MB ebf465b6 download
Q4_K 3 files 2.23 GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q4_K.gguf 770 MB b64e4ecd download
llama3.2-1b-instruct-hasanpiker-abliterated.Q4_K_M.gguf 770 MB b64e4ecd download
llama3.2-1b-instruct-hasanpiker-abliterated.Q4_K_S.gguf 740 MB f1007dd9 download
IQ4 2 files 1.42 GB
llama3.2-1b-instruct-hasanpiker-abliterated.IQ4_NL.gguf 741 MB 4b7a3c0c download
llama3.2-1b-instruct-hasanpiker-abliterated.IQ4_XS.gguf 714 MB 39db48da download
Q3_K 4 files 2.57 GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q3_K_L.gguf 699 MB f6469e3c download
llama3.2-1b-instruct-hasanpiker-abliterated.Q3_K.gguf 659 MB f31b5b87 download
llama3.2-1b-instruct-hasanpiker-abliterated.Q3_K_M.gguf 659 MB f31b5b87 download
llama3.2-1b-instruct-hasanpiker-abliterated.Q3_K_S.gguf 612 MB 092148f8 download
IQ3 3 files 1.79 GB
llama3.2-1b-instruct-hasanpiker-abliterated.IQ3_M.gguf 627 MB 0de3a466 download
llama3.2-1b-instruct-hasanpiker-abliterated.IQ3_S.gguf 614 MB 77faabaf download
llama3.2-1b-instruct-hasanpiker-abliterated.IQ3_XS.gguf 592 MB ca341dfd download
Q2_K 1 file 554 MB
llama3.2-1b-instruct-hasanpiker-abliterated.Q2_K.gguf 554 MB f76053c2 download
Auxiliary files 2 files 9.80 KB
README.md 6.37 KB 2b4c56e7 download
.gitattributes 3.44 KB 9523bc2c download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama3.2-1b-instruct-hasanpiker-abliterated - GGUF

Name Quant method Size
llama3.2-1b-instruct-hasanpiker-abliterated.Q2_K.gguf Q2_K 0.54GB
llama3.2-1b-instruct-hasanpiker-abliterated.IQ3_XS.gguf IQ3_XS 0.58GB
llama3.2-1b-instruct-hasanpiker-abliterated.IQ3_S.gguf IQ3_S 0.6GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q3_K_S.gguf Q3_K_S 0.6GB
llama3.2-1b-instruct-hasanpiker-abliterated.IQ3_M.gguf IQ3_M 0.61GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q3_K.gguf Q3_K 0.64GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q3_K_M.gguf Q3_K_M 0.64GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q3_K_L.gguf Q3_K_L 0.68GB
llama3.2-1b-instruct-hasanpiker-abliterated.IQ4_XS.gguf IQ4_XS 0.7GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q4_0.gguf Q4_0 0.72GB
llama3.2-1b-instruct-hasanpiker-abliterated.IQ4_NL.gguf IQ4_NL 0.72GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q4_K_S.gguf Q4_K_S 0.72GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q4_K.gguf Q4_K 0.75GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q4_K_M.gguf Q4_K_M 0.75GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q4_1.gguf Q4_1 0.77GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q5_0.gguf Q5_0 0.83GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q5_K_S.gguf Q5_K_S 0.83GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q5_K.gguf Q5_K 0.85GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q5_K_M.gguf Q5_K_M 0.85GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q5_1.gguf Q5_1 0.89GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q6_K.gguf Q6_K 0.95GB
llama3.2-1b-instruct-hasanpiker-abliterated.Q8_0.gguf Q8_0 1.23GB

Original model description:

base_model: huihui-ai/Llama-3.2-1B-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-3.2-1B-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. 2025-02-14uploaded readme28697cd6.4 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