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

gaianet/Llama-3.2-3B-Instruct-Uncensored-GGUF

gaianet Llama 3B GGUF second-order 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/gaianet%2FLlama-3.2-3B-Instruct-Uncensored-GGUF"
Response includes
  • classification m-uncensored
  • files 16
  • hub_downloads_all_time 5,092
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=gaianet
All 2 models by gaianet
 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
5K
241 last 30d - cooling
Likes
0
Model age
20mo ago
created 2025-02-13
Downloads over time
Now5.1K→from379↑1,259%
1412K3.8K5.6K379 on Feb 12, 20255.1K on Oct 11Feb '25May '25Aug '25Nov '25FebMayAug
Feb 12, 2025 → Oct 11 · 126 snapshots · spans 606 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.

thirdeyeai/Llama-3.2-3B-Instruct-Uncensored↓ 23 this lineage
gaianet/Llama-3.2-3B-Instruct-Uncensored-GGUF↓ 241

Metadata

Quantizations
F16 Q2_K Q3_K Q4 Q4_K Q5 Q5_K Q6_K Q8_0
Tags
transformers gguf llama text-generation base_model:thirdeyeai/Llama-3.2-3B-Instruct-Uncensored base_model:quantized:thirdeyeai/Llama-3.2-3B-Instruct-Uncensored endpoints_compatible region:us conversational

Related

Other by gaianet
Llama-3-8B-Lexi-Uncensored-GGUF 10
Same base model
second-state/Llama-3.2-3B-Instruct-Uncensored-GGUF 609
Total size
32.9 GB
Files
16
Quantizations
10
Registered
2026-08-22 13:56
Last updated on HF
2025-02-13 13:48
Source huggingface.co/gaianet/Llama-3.2-3B-Instruct-Uncensored-GGUF ↗ Base model thirdeyeai/Llama-3.2-3B-Instruct-Uncensored →

Files by quantization

F16 1 file 6.73 GB
Llama-3.2-3B-Instruct-Uncensored-f16.gguf 6.73 GB b86930d8 download
Q8_0 1 file 3.58 GB
Llama-3.2-3B-Instruct-Uncensored-Q8_0.gguf 3.58 GB 828a4645 download
Q6_K 1 file 2.76 GB
Llama-3.2-3B-Instruct-Uncensored-Q6_K.gguf 2.76 GB 7eb811a9 download
Q5_K 2 files 4.78 GB
Llama-3.2-3B-Instruct-Uncensored-Q5_K_M.gguf 2.41 GB 894c7e8b download
Llama-3.2-3B-Instruct-Uncensored-Q5_K_S.gguf 2.37 GB 38ed3cf5 download
Q5 1 file 2.37 GB
Llama-3.2-3B-Instruct-Uncensored-Q5_0.gguf 2.37 GB d99d0421 download
Q4_K 2 files 4.09 GB
Llama-3.2-3B-Instruct-Uncensored-Q4_K_M.gguf 2.09 GB 29036fac download
Llama-3.2-3B-Instruct-Uncensored-Q4_K_S.gguf 2.00 GB 52e020d6 download
Q4 1 file 1.99 GB
Llama-3.2-3B-Instruct-Uncensored-Q4_0.gguf 1.99 GB 42911166 download
Q3_K 3 files 5.17 GB
Llama-3.2-3B-Instruct-Uncensored-Q3_K_L.gguf 1.85 GB 0fe55926 download
Llama-3.2-3B-Instruct-Uncensored-Q3_K_M.gguf 1.73 GB a7df6a19 download
Llama-3.2-3B-Instruct-Uncensored-Q3_K_S.gguf 1.59 GB 38e8c429 download
Q2_K 1 file 1.39 GB
Llama-3.2-3B-Instruct-Uncensored-Q2_K.gguf 1.39 GB d09e6abd download
Auxiliary files 3 files 4.07 KB
.gitattributes 2.50 KB 706e542e download
config.json 928 B 8801edd0 download
README.md 676 B 3e23c77d download

README current version from Hugging Face

base_model: thirdeyeai/Llama-3.2-3B-Instruct-Uncensored
model_creator: thirdeyeai
model_name: Llama-3.2-3B-Instruct-Uncensored
quantized_by: Second State Inc.
library_name: transformers

Llama-3.2-3B-Instruct-Uncensored-GGUF

Original Model

thirdeyeai/Llama-3.2-3B-Instruct-Uncensored

Run with Gaianet

Prompt template

prompt template: llama-3-chat

Context size

chat_ctx_size: 128000

Run with GaiaNet

Quantized with llama.cpp b4681

README history 2 versions

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

  1. 2025-02-13Update README.md2f83565676 B
    Loading...
  2. 2025-02-13initial commitbc798a428 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