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

ModelsLab/Llama-3-uncensored-Dare-1

ModelsLab Llama 8.0B
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/ModelsLab%2FLlama-3-uncensored-Dare-1"
Response includes
  • classification m5
  • files 25
  • hub_downloads_all_time 2,676
  • providers 1
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=ModelsLab
All 3 models by ModelsLab
 GET/models?family=llama&method=m5
Sibling llama models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

No other method signals detected in this model.
Confidence
MEDIUM
Why this label 3 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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • no abliteration marker
How we label → About M5 →
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
3K
23 last 30d - cooling
Likes
2
Descendants
3
in 3 direct forks
Model age
2.3y ago
created 2024-06-27
Available via
1 provider
featherless-ai
Downloads over time
Now2.7K→from212↑1,165%
09822K2.9K212 on Jul 24, 20242.7K on Oct 122.7K on Oct 9Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 12 · 156 snapshots · spans 810 days

Genealogy 3 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.

ModelsLab/Llama-3-uncensored-Dare-1↓ 23 3 forks
featherless-ai-quants/ModelsLab-Llama-3-uncensored-Dare-1-GGUF↓ 872
mradermacher/Llama-3-uncensored-Dare-1-GGUF↓ 481
tensorblock/Llama-3-uncensored-Dare-1-GGUF↓ 108

Metadata

License
apache-2.0
Tags
transformers safetensors llama text-generation merge mergekit lazymergekit nbeerbower/llama-3-spicy-abliterated-stella-8B Azazelle/L3-RP_io aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K conversational license:apache-2.0

Related

Other by ModelsLab
Llama-3.1-8b-Uncensored-Dare 68 uncensored_chat_image 0
Total size
15.0 GB
Files
25
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-06-27 20:24
Source huggingface.co/ModelsLab/Llama-3-uncensored-Dare-1 ↗

Files by quantization

Auxiliary files 25 files 15.0 GB
model-00002-of-00017.safetensors 1002 MB cc75dedb download
model-00001-of-00017.safetensors 1002 MB 50cb4f8f download
model-00005-of-00017.safetensors 952 MB 1f3313f9 download
model-00009-of-00017.safetensors 952 MB 633e8e45 download
model-00013-of-00017.safetensors 952 MB f0aacae7 download
model-00003-of-00017.safetensors 944 MB 0e2b0be6 download
model-00004-of-00017.safetensors 944 MB 56fc5ea3 download
model-00007-of-00017.safetensors 944 MB 7b3c1019 download
model-00011-of-00017.safetensors 944 MB a8a76766 download
model-00012-of-00017.safetensors 944 MB 74e96989 download
model-00008-of-00017.safetensors 944 MB 923bcc42 download
model-00015-of-00017.safetensors 944 MB 1fd41f9a download
model-00016-of-00017.safetensors 944 MB 1a450418 download
model-00006-of-00017.safetensors 904 MB b3cb9805 download
model-00010-of-00017.safetensors 904 MB 2cc1a078 download
model-00014-of-00017.safetensors 904 MB 0828a077 download
model-00017-of-00017.safetensors 192 MB 81e6bc8c download
tokenizer.json 8.66 MB 9e740002 download
tokenizer_config.json 49.8 KB 68b20e0c download
model.safetensors.index.json 22.3 KB 2cb1f101 download
.gitattributes 1.48 KB a6344aac download
README.md 1.12 KB 321f0d14 download
config.json 730 B a55d98e7 download
mergekit_config.yml 490 B 3db9868d download
special_tokens_map.json 444 B 278b7f0f download

README current version from Hugging Face

license: apache-2.0
tags:

  • merge
  • mergekit
  • lazymergekit
  • nbeerbower/llama-3-spicy-abliterated-stella-8B
  • Azazelle/L3-RP_io
  • aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K

Llama 3 Dare

Llama 3 Dare is a merge of the following models using mergekit:

🧩 Configuration

models:
  - model: Orenguteng/Llama-3-8B-Lexi-Uncensored
  - model: nbeerbower/llama-3-spicy-abliterated-stella-8B
    parameters:
      density: 0.53
      weight: 0.4
  - model: Azazelle/L3-RP_io
    parameters:
      density: 0.53
      weight: 0.3
  - model: aifeifei798/llama3-8B-DarkIdol-2.1-Uncensored-1048K
    parameters:
      density: 0.53
      weight: 0.3
merge_method: dare_ties
base_model: Orenguteng/Llama-3-8B-Lexi-Uncensored
parameters:
  int8_mask: true
dtype: bfloat16

README history 1 version

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

  1. 2024-06-27Upload folder using huggingface_hub5d6ea4b1.1 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