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

RichardErkhov/huihui-ai_-_Llama-3.2-1B-Instruct-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%2Fhuihui-ai_-_Llama-3.2-1B-Instruct-abliterated-gguf"
Response includes
  • classification m8
  • files 24
  • hub_downloads_all_time 12,886
  • 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
13K
2K last 30d - stable
Likes
1
Model age
2.0y ago
created 2024-10-03
Downloads over time
Now13.7K→from501↑2,635%
05K10K15.1K501 on Oct 2, 202413.7K on Oct 12Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 2, 2024 → Oct 12 · 147 snapshots · spans 740 days

Variants by this author 2 formats · 2K 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 conversational

Related

Other by RichardErkhov
byroneverson_-_gemma-2-27b-it-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 huihui-ai_-_Llama-3.2-3B-Instruct-abliterated-gguf 2K
Total size
19.6 GB
Files
24
Quantizations
11
Registered
2026-08-22 13:56
Last updated on HF
2024-10-03 17:34
Source huggingface.co/RichardErkhov/huihui-ai_-_Llama-3.2-1B-Instruct-abliterated-gguf ↗

Files by quantization

Q8_0 1 file 1.49 GB
Llama-3.2-1B-Instruct-abliterated.Q8_0.gguf 1.49 GB e3074a9e download
Q6_K 1 file 1.15 GB
Llama-3.2-1B-Instruct-abliterated.Q6_K.gguf 1.15 GB 701db8fe download
Q5 2 files 2.07 GB
Llama-3.2-1B-Instruct-abliterated.Q5_1.gguf 1.07 GB 785694aa download
Llama-3.2-1B-Instruct-abliterated.Q5_0.gguf 1023 MB 65b12b35 download
Q5_K 3 files 3.03 GB
Llama-3.2-1B-Instruct-abliterated.Q5_K.gguf 1.02 GB ea28944e download
Llama-3.2-1B-Instruct-abliterated.Q5_K_M.gguf 1.02 GB ea28944e download
Llama-3.2-1B-Instruct-abliterated.Q5_K_S.gguf 1023 MB 3b096185 download
Q4 2 files 1.78 GB
Llama-3.2-1B-Instruct-abliterated.Q4_1.gguf 950 MB 52ef9c43 download
Llama-3.2-1B-Instruct-abliterated.Q4_0.gguf 876 MB 3e852031 download
Q4_K 3 files 2.64 GB
Llama-3.2-1B-Instruct-abliterated.Q4_K.gguf 911 MB 2ee12dd7 download
Llama-3.2-1B-Instruct-abliterated.Q4_K_M.gguf 911 MB 2ee12dd7 download
Llama-3.2-1B-Instruct-abliterated.Q4_K_S.gguf 881 MB 5251286a download
IQ4 2 files 1.69 GB
Llama-3.2-1B-Instruct-abliterated.IQ4_NL.gguf 882 MB 59434994 download
Llama-3.2-1B-Instruct-abliterated.IQ4_XS.gguf 847 MB 27b52707 download
Q3_K 4 files 2.99 GB
Llama-3.2-1B-Instruct-abliterated.Q3_K_L.gguf 806 MB 38cf930c download
Llama-3.2-1B-Instruct-abliterated.Q3_K.gguf 766 MB e3e5b8b0 download
Llama-3.2-1B-Instruct-abliterated.Q3_K_M.gguf 766 MB e3e5b8b0 download
Llama-3.2-1B-Instruct-abliterated.Q3_K_S.gguf 720 MB b45f4840 download
IQ3 3 files 2.11 GB
Llama-3.2-1B-Instruct-abliterated.IQ3_M.gguf 734 MB f364faf4 download
Llama-3.2-1B-Instruct-abliterated.IQ3_S.gguf 722 MB cef403f9 download
Llama-3.2-1B-Instruct-abliterated.IQ3_XS.gguf 700 MB db5c4e59 download
Q2_K 1 file 636 MB
Llama-3.2-1B-Instruct-abliterated.Q2_K.gguf 636 MB d7209d4e download
Auxiliary files 2 files 9.53 KB
README.md 6.31 KB bb73c7e4 download
.gitattributes 3.22 KB b279a21d download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

Llama-3.2-1B-Instruct-abliterated - GGUF

Name Quant method Size
Llama-3.2-1B-Instruct-abliterated.Q2_K.gguf Q2_K 0.62GB
Llama-3.2-1B-Instruct-abliterated.IQ3_XS.gguf IQ3_XS 0.68GB
Llama-3.2-1B-Instruct-abliterated.IQ3_S.gguf IQ3_S 0.7GB
Llama-3.2-1B-Instruct-abliterated.Q3_K_S.gguf Q3_K_S 0.7GB
Llama-3.2-1B-Instruct-abliterated.IQ3_M.gguf IQ3_M 0.72GB
Llama-3.2-1B-Instruct-abliterated.Q3_K.gguf Q3_K 0.75GB
Llama-3.2-1B-Instruct-abliterated.Q3_K_M.gguf Q3_K_M 0.75GB
Llama-3.2-1B-Instruct-abliterated.Q3_K_L.gguf Q3_K_L 0.79GB
Llama-3.2-1B-Instruct-abliterated.IQ4_XS.gguf IQ4_XS 0.83GB
Llama-3.2-1B-Instruct-abliterated.Q4_0.gguf Q4_0 0.86GB
Llama-3.2-1B-Instruct-abliterated.IQ4_NL.gguf IQ4_NL 0.86GB
Llama-3.2-1B-Instruct-abliterated.Q4_K_S.gguf Q4_K_S 0.86GB
Llama-3.2-1B-Instruct-abliterated.Q4_K.gguf Q4_K 0.89GB
Llama-3.2-1B-Instruct-abliterated.Q4_K_M.gguf Q4_K_M 0.89GB
Llama-3.2-1B-Instruct-abliterated.Q4_1.gguf Q4_1 0.93GB
Llama-3.2-1B-Instruct-abliterated.Q5_0.gguf Q5_0 1.0GB
Llama-3.2-1B-Instruct-abliterated.Q5_K_S.gguf Q5_K_S 1.0GB
Llama-3.2-1B-Instruct-abliterated.Q5_K.gguf Q5_K 1.02GB
Llama-3.2-1B-Instruct-abliterated.Q5_K_M.gguf Q5_K_M 1.02GB
Llama-3.2-1B-Instruct-abliterated.Q5_1.gguf Q5_1 1.07GB
Llama-3.2-1B-Instruct-abliterated.Q6_K.gguf Q6_K 1.15GB
Llama-3.2-1B-Instruct-abliterated.Q8_0.gguf Q8_0 1.49GB

Original model description:

library_name: transformers
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:

  • abliterated
  • uncensored

🦙 Llama-3.2-1B-Instruct-abliterated

This is an uncensored version of Llama 3.2 1B Instruct created with abliteration (see this article to know more about it).

Special thanks to @FailSpy for the original code and technique. Please follow him if you're interested in abliterated models.

Evaluations

The following data has been re-evaluated and calculated as the average for each test.

Benchmark Llama-3.2-3B-Instruct Llama-3.2-3B-Instruct-abliterated
IF_Eval 58.50 56.88
MMLU Pro 16.35 14.35
TruthfulQA 43.08 38.96
BBH 33.75 31.83
GPQA 25.96 26.39
The script used for evaluation can be found inside this repository under /eval.sh, or click here

README history 1 version

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

  1. 2024-10-03uploaded readmeeb1a0ce6.3 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