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

RichardErkhov/Dogge_-_llama-3-70B-instruct-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-instruct-uncensored-gguf"
Response includes
  • classification m8
  • files 12
  • hub_downloads_all_time 7,320
  • 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
7K
415 last 30d - cooling
Likes
0
Model age
2.1y ago
created 2024-09-04
Downloads over time
Now7.4K→from637↑1,062%
02.7K5.4K8.1K637 on Sep 4, 20247.4K on Oct 11Sep '24Jan '25May '25Sep '25JanMaySep
Sep 4, 2024 → Oct 11 · 149 snapshots · spans 767 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
288 GB
Files
12
Quantizations
6
Registered
2026-08-22 13:56
Last updated on HF
2024-09-04 21:53
Source huggingface.co/RichardErkhov/Dogge_-_llama-3-70B-instruct-uncensored-gguf ↗

Files by quantization

Q4 1 file 37.2 GB
llama-3-70B-instruct-uncensored.Q4_0.gguf 37.2 GB de435230 download
IQ4 1 file 35.6 GB
llama-3-70B-instruct-uncensored.IQ4_XS.gguf 35.6 GB 4feaef30 download
Q3_K 4 files 127 GB
llama-3-70B-instruct-uncensored.Q3_K_L.gguf 34.6 GB 15b234dd download
llama-3-70B-instruct-uncensored.Q3_K.gguf 31.9 GB c4df0543 download
llama-3-70B-instruct-uncensored.Q3_K_M.gguf 31.9 GB c4df0543 download
llama-3-70B-instruct-uncensored.Q3_K_S.gguf 28.8 GB cec4843e download
IQ3 3 files 66.9 GB
llama-3-70B-instruct-uncensored.IQ3_M.gguf 29.7 GB bf5c42ee download
llama-3-70B-instruct-uncensored.IQ3_S.gguf 27.6 GB d60da37d download
llama-3-70B-instruct-uncensored.IQ3_XS.gguf 9.61 GB 7db352fe download
Q2_K 1 file 20.8 GB
llama-3-70B-instruct-uncensored.Q2_K.gguf 20.8 GB 4f4fba28 download
Auxiliary files 2 files 9.49 KB
README.md 4.89 KB 5d1a68d0 download
.gitattributes 4.59 KB 8a25be88 download

README current version from Hugging Face

Quantization made by Richard Erkhov.

Github

Discord

Request more models

llama-3-70B-instruct-uncensored - GGUF

Name Quant method Size
llama-3-70B-instruct-uncensored.Q2_K.gguf Q2_K 20.78GB
llama-3-70B-instruct-uncensored.IQ3_XS.gguf IQ3_XS 9.61GB
llama-3-70B-instruct-uncensored.IQ3_S.gguf IQ3_S 27.58GB
llama-3-70B-instruct-uncensored.Q3_K_S.gguf Q3_K_S 28.79GB
llama-3-70B-instruct-uncensored.IQ3_M.gguf IQ3_M 29.74GB
llama-3-70B-instruct-uncensored.Q3_K.gguf Q3_K 31.91GB
llama-3-70B-instruct-uncensored.Q3_K_M.gguf Q3_K_M 31.91GB
llama-3-70B-instruct-uncensored.Q3_K_L.gguf Q3_K_L 34.59GB
llama-3-70B-instruct-uncensored.IQ4_XS.gguf IQ4_XS 35.64GB
llama-3-70B-instruct-uncensored.Q4_0.gguf Q4_0 37.22GB
llama-3-70B-instruct-uncensored.IQ4_NL.gguf IQ4_NL 37.58GB
llama-3-70B-instruct-uncensored.Q4_K_S.gguf Q4_K_S 37.58GB
llama-3-70B-instruct-uncensored.Q4_K.gguf Q4_K 39.6GB
llama-3-70B-instruct-uncensored.Q4_K_M.gguf Q4_K_M 39.6GB
llama-3-70B-instruct-uncensored.Q4_1.gguf Q4_1 41.27GB
llama-3-70B-instruct-uncensored.Q5_0.gguf Q5_0 45.32GB
llama-3-70B-instruct-uncensored.Q5_K_S.gguf Q5_K_S 45.32GB
llama-3-70B-instruct-uncensored.Q5_K.gguf Q5_K 46.52GB
llama-3-70B-instruct-uncensored.Q5_K_M.gguf Q5_K_M 46.52GB
llama-3-70B-instruct-uncensored.Q5_1.gguf Q5_1 49.36GB
llama-3-70B-instruct-uncensored.Q6_K.gguf Q6_K 53.91GB
llama-3-70B-instruct-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-Instruct-bnb-4bit

Uploaded model

  • Developed by: Dogge
  • License: apache-2.0
  • Finetuned from model : unsloth/llama-3-70b-Instruct-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. 2024-09-04uploaded readme42a676f4.9 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