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

RichardErkhov/Dogge_-_llama-3-70B-uncensored-gguf

RichardErkhov Llama 70B GGUF 8K 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%2FDogge_-_llama-3-70B-uncensored-gguf"
Response includes
  • classification m8
  • files 12
  • hub_downloads_all_time 5,575
  • 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
731 last 30d - stable
Likes
0
Model age
2.0y ago
created 2024-10-09
Downloads over time
Now5.7K→from790↑621%
02.1K4.2K6.3K790 on Oct 9, 20245.7K on Oct 11Oct '24Feb '25Jun '25Oct '25FebJunOct
Oct 9, 2024 → Oct 11 · 144 snapshots · spans 732 days

Metadata

Quantizations
IQ3 IQ4 Q2_K Q3_K Q4
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
310 GB
Files
12
Quantizations
6
Registered
2026-08-22 13:56
Last updated on HF
2024-10-09 23:52
Source huggingface.co/RichardErkhov/Dogge_-_llama-3-70B-uncensored-gguf ↗

Files by quantization

Q4 1 file 37.2 GB
llama-3-70B-uncensored.Q4_0.gguf 37.2 GB 8cf89b63 download
IQ4 1 file 35.6 GB
llama-3-70B-uncensored.IQ4_XS.gguf 35.6 GB 07f17d35 download
Q3_K 4 files 127 GB
llama-3-70B-uncensored.Q3_K_L.gguf 34.6 GB 256d7a34 download
llama-3-70B-uncensored.Q3_K.gguf 31.9 GB 3a2bb652 download
llama-3-70B-uncensored.Q3_K_M.gguf 31.9 GB 3a2bb652 download
llama-3-70B-uncensored.Q3_K_S.gguf 28.8 GB 351edcae download
IQ3 3 files 85.8 GB
llama-3-70B-uncensored.IQ3_M.gguf 29.7 GB 92ac8176 download
llama-3-70B-uncensored.IQ3_S.gguf 28.8 GB 3eb441a2 download
llama-3-70B-uncensored.IQ3_XS.gguf 27.3 GB 9c43e180 download
Q2_K 1 file 24.6 GB
llama-3-70B-uncensored.Q2_K.gguf 24.6 GB 28cb5867 download
Auxiliary files 2 files 8.68 KB
README.md 4.38 KB 923050ba download
.gitattributes 4.29 KB ddd935b1 download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-70B-uncensored - GGUF

Name Quant method Size
llama-3-70B-uncensored.Q2_K.gguf Q2_K 24.56GB
llama-3-70B-uncensored.IQ3_XS.gguf IQ3_XS 27.29GB
llama-3-70B-uncensored.IQ3_S.gguf IQ3_S 28.79GB
llama-3-70B-uncensored.Q3_K_S.gguf Q3_K_S 28.79GB
llama-3-70B-uncensored.IQ3_M.gguf IQ3_M 29.74GB
llama-3-70B-uncensored.Q3_K.gguf Q3_K 31.91GB
llama-3-70B-uncensored.Q3_K_M.gguf Q3_K_M 31.91GB
llama-3-70B-uncensored.Q3_K_L.gguf Q3_K_L 34.59GB
llama-3-70B-uncensored.IQ4_XS.gguf IQ4_XS 35.64GB
llama-3-70B-uncensored.Q4_0.gguf Q4_0 37.22GB
llama-3-70B-uncensored.IQ4_NL.gguf IQ4_NL 37.58GB
llama-3-70B-uncensored.Q4_K_S.gguf Q4_K_S 37.58GB
llama-3-70B-uncensored.Q4_K.gguf Q4_K 39.6GB
llama-3-70B-uncensored.Q4_K_M.gguf Q4_K_M 39.6GB
llama-3-70B-uncensored.Q4_1.gguf Q4_1 41.27GB
llama-3-70B-uncensored.Q5_0.gguf Q5_0 45.32GB
llama-3-70B-uncensored.Q5_K_S.gguf Q5_K_S 45.32GB
llama-3-70B-uncensored.Q5_K.gguf Q5_K 46.52GB
llama-3-70B-uncensored.Q5_K_M.gguf Q5_K_M 46.52GB
llama-3-70B-uncensored.Q5_1.gguf Q5_1 49.36GB
llama-3-70B-uncensored.Q6_K.gguf Q6_K 53.91GB
llama-3-70B-uncensored.Q8_0.gguf Q8_0 69.83GB

Original model description:

language:

  • en
    license: apache-2.0
    tags:
  • text-generation-inference
  • transformers
  • unsloth
  • llama
  • trl
  • sft
    base_model: unsloth/llama-3-70b-bnb-4bit

Uploaded model

  • Developed by: Dogge
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3-70b-bnb-4bit

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. 2024-10-09uploaded readme30556ac4.4 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