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

mradermacher/Meta-Llama-3.1-405B-Instruct-Uncensored-GGUF

mradermacher Llama 405B second-order
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/mradermacher%2FMeta-Llama-3.1-405B-Instruct-Uncensored-GGUF"
Response includes
  • classification m-uncensored
  • files 74
  • author_summary 3324 models
  • readme_text full
Try next
GET/models?author=mradermacher
All 3324 models by mradermacher
 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 · 30-day
0
Likes
3
Model age
2.1y ago
created 2024-09-14

Training datasets

1 of 1 in /datasets

Corpora the author lists in the model card. Datasets tracked in our /datasets catalog carry a category badge linking to the workflow stage. Others open on Hugging Face.

Guilherme34/uncensor misc
Downloads over time
Now0→from0↑0%
00110 on Sep 11, 20240 on Oct 11Sep '24Jan '25May '25Sep '25JanMaySep
Sep 11, 2024 → Oct 11 · 148 snapshots · spans 760 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.

nicoboss/Meta-Llama-3.1-405B-Instruct-Uncensored this lineage
mradermacher/Meta-Llama-3.1-405B-Instruct-Uncensored-GGUF

Variants by this author 2 formats · 0 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

License
llama3.1
Languages
en
Tags
transformers generated_from_trainer en dataset:Guilherme34/uncensor base_model:nicoboss/Meta-Llama-3.1-405B-Instruct-Uncensored base_model:finetune:nicoboss/Meta-Llama-3.1-405B-Instruct-Uncensored license:llama3.1 endpoints_compatible region:us

Related

Other by mradermacher
Ornith-1.5-9B-uncensored-GGUF 1.5M Qwen3-VL-8B-Instruct-abliterated-GGUF 667K Qwen3.8-Flash-Next-Uncensored-i1-GGUF 153K gemma-4-26B-A4B-it-ultra-uncensored-heretic-i1-GGUF 138K Qwen3.8-9B-heretic-uncensored-GGUF 106K
Same base model
mradermacher/Meta-Llama-3.1-405B-Instruct-Uncensored-i1-GGUF 0
Total size
0 B
Files
74
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-09-16 18:05
Source huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-Uncensored-GGUF ↗ Base model nicoboss/Meta-Llama-3.1-405B-Instruct-Uncensored →

Files by quantization

Auxiliary files 74 files 2.98 TB
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_M.gguf.part1of4 46.0 GB f82df3d5 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_M.gguf.part2of4 46.0 GB a7711615 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_M.gguf.part3of4 46.0 GB 3fbd9948 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q4_K_M.gguf.part1of5 46.0 GB 31cbdd6a download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q4_K_M.gguf.part2of5 46.0 GB 11e033db download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q4_K_M.gguf.part3of5 46.0 GB 6eb4231a download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q4_K_M.gguf.part4of5 46.0 GB 0e8efee2 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_M.gguf.part1of6 45.0 GB c4b6b0a7 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_M.gguf.part2of6 45.0 GB fc7d7ea0 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_M.gguf.part3of6 45.0 GB 9ca65143 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_M.gguf.part4of6 45.0 GB 5a0f6b87 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_M.gguf.part5of6 45.0 GB ecd7b7cf download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q6_K.gguf.part1of7 45.0 GB 89a856a8 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q6_K.gguf.part2of7 45.0 GB ab761619 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q6_K.gguf.part3of7 45.0 GB e25fb417 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q6_K.gguf.part4of7 45.0 GB a5e886a6 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q6_K.gguf.part5of7 45.0 GB 016f0a03 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q6_K.gguf.part6of7 45.0 GB 35b56e54 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q8_0.gguf.part1of9 45.0 GB 8095db29 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q8_0.gguf.part2of9 45.0 GB 19cce8e1 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q8_0.gguf.part3of9 45.0 GB dcab26a7 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q8_0.gguf.part4of9 45.0 GB 0c88296f download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q8_0.gguf.part5of9 45.0 GB d6b51f99 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q8_0.gguf.part6of9 45.0 GB 2ea282ca download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q8_0.gguf.part7of9 45.0 GB 8c18889f download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q8_0.gguf.part8of9 45.0 GB 06db1e7c download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_S.gguf.part1of6 44.0 GB e9b86606 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_S.gguf.part2of6 44.0 GB 9af01dca download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_S.gguf.part3of6 44.0 GB be66ceb8 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_S.gguf.part4of6 44.0 GB f16be83e download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_S.gguf.part5of6 44.0 GB d71b29ea download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_M.gguf.part4of4 44.0 GB 4482a283 download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_M.gguf.part1of4 43.0 GB faaf5bc0 download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_M.gguf.part2of4 43.0 GB 9860d5b3 download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_M.gguf.part3of4 43.0 GB 9d3370d3 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q4_K_S.gguf.part1of5 43.0 GB 8612b9a5 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q4_K_S.gguf.part2of5 43.0 GB fb7d01f8 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q4_K_S.gguf.part3of5 43.0 GB 0d855488 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q4_K_S.gguf.part4of5 43.0 GB 31014d41 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q4_K_S.gguf.part5of5 42.7 GB 8629f915 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q4_K_M.gguf.part5of5 42.4 GB a5e4b54f download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_M.gguf.part6of6 42.0 GB 8787e376 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q8_0.gguf.part9of9 41.6 GB 1a55e7a5 download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_S.gguf.part1of4 41.0 GB 2878074a download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_S.gguf.part2of4 41.0 GB 776c8425 download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_S.gguf.part3of4 41.0 GB b9d360bb download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ4_XS.gguf.part1of5 41.0 GB f564b98b download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ4_XS.gguf.part2of5 41.0 GB 3c24523b download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ4_XS.gguf.part3of5 41.0 GB 490e8efe download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ4_XS.gguf.part4of5 41.0 GB 3c9a784d download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_S.gguf.part1of4 41.0 GB 558f0f78 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_S.gguf.part2of4 41.0 GB 20e723fe download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_S.gguf.part3of4 41.0 GB 776141da download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_S.gguf.part4of4 40.5 GB 22858396 download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_M.gguf.part4of4 40.3 GB 379006ac download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_S.gguf.part4of4 40.2 GB 006cc631 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q5_K_S.gguf.part6of6 40.1 GB a938ef26 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q6_K.gguf.part7of7 40.1 GB c590de14 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_L.gguf.part1of5 40.0 GB 5f841040 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_L.gguf.part2of5 40.0 GB d3ec4bfd download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_L.gguf.part3of5 40.0 GB ea44544c download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_L.gguf.part4of5 40.0 GB 92910032 download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ4_XS.gguf.part5of5 39.6 GB 1abf76df download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_XS.gguf.part1of4 39.0 GB 45d84751 download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_XS.gguf.part2of4 39.0 GB 4142918b download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_XS.gguf.part3of4 39.0 GB 1b995880 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q3_K_L.gguf.part5of5 38.2 GB 1d6e966b download
Meta-Llama-3.1-405B-Instruct-Uncensored.IQ3_XS.gguf.part4of4 37.7 GB 79ade357 download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q2_K.gguf.part1of4 35.0 GB cbebe03b download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q2_K.gguf.part2of4 35.0 GB 6f147c2e download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q2_K.gguf.part3of4 35.0 GB a559582b download
Meta-Llama-3.1-405B-Instruct-Uncensored.Q2_K.gguf.part4of4 34.1 GB 2c989a95 download
README.md 13.4 KB 3cc85ac9 download
.gitattributes 8.26 KB fb8ae3bc download

README current version from Hugging Face

base_model: nicoboss/Meta-Llama-3.1-405B-Instruct-Uncensored
datasets:

  • Guilherme34/uncensor
    language:
  • en
    library_name: transformers
    license: llama3.1
    quantized_by: mradermacher
    tags:
  • generated_from_trainer

About

static quants of https://huggingface.co/nicoboss/Meta-Llama-3.1-405B-Instruct-Uncensored

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Meta-Llama-3.1-405B-Instruct-Uncensored-i1-GGUF

Usage

If you are unsure how to use GGUF files, refer to one of TheBloke's
READMEs for
more details, including on how to concatenate multi-part files.

Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Link Type Size/GB Notes
PART 1 PART 2 PART 3 PART 4 Q2_K 149.4
PART 1 PART 2 PART 3 PART 4 IQ3_XS 166.2
PART 1 PART 2 PART 3 PART 4 Q3_K_S 175.3
PART 1 PART 2 PART 3 PART 4 IQ3_S 175.6 beats Q3_K*
PART 1 PART 2 PART 3 PART 4 IQ3_M 181.8
PART 1 PART 2 PART 3 PART 4 Q3_K_M 195.5 lower quality
P1 P2 P3 P4 P5 Q3_K_L 212.9
P1 P2 P3 P4 P5 IQ4_XS 218.7
P1 P2 P3 P4 P5 Q4_K_S 230.6 fast, recommended
P1 P2 P3 P4 P5 Q4_K_M 243.2 fast, recommended
P1 P2 P3 P4 P5 P6 Q5_K_S 279.4
P1 P2 P3 P4 P5 P6 Q5_K_M 286.7
P1 P2 P3 P4 P5 P6 P7 Q6_K 333.0 very good quality
P1 P2 P3 P4 P5 P6 P7 P8 P9 Q8_0 431.3 fast, best quality

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

image.png

And here are Artefact2's thoughts on the matter:
https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9

FAQ / Model Request

See https://huggingface.co/mradermacher/model_requests for some answers to
questions you might have and/or if you want some other model quantized.

Thanks

I thank my company, nethype GmbH, for letting
me use its servers and providing upgrades to my workstation to enable
this work in my free time.

README history 3 versions

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

  1. 2024-09-16auto-patch README.mda3b4f6313.4 KB
    Loading...
  2. 2024-09-16auto-patch README.mdbbb5c4611.7 KB
    Loading...
  3. 2024-09-14uploaded from nethype/marco5af8941238 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