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

backyardai/Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF

backyardai Llama 70B GGUF second-order 262K 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/backyardai%2FLlama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF"
Response includes
  • classification m-uncensored
  • files 33
  • hub_downloads_all_time 22,159
  • author_summary 1 models
  • readme_text full
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
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
22K
2K last 30d - cooling
Likes
3
Model age
2.3y ago
created 2024-06-07
Downloads over time
Now22.3K→from1.5K↑1,401%
08.1K16.3K24.4K1.5K on Jul 24, 202422.3K on Oct 11Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 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.

Metadata

Quantizations
IQ1 IQ2 IQ3 IQ4 Q3_K Q4_K Q5_K
Tags
gguf uncencored llama-3 tess lumimaid Lumi-tess base_model:ryzen88/Llama-3-70b-Uncensored-Lumi-Tess-gradient base_model:quantized:ryzen88/Llama-3-70b-Uncensored-Lumi-Tess-gradient endpoints_compatible region:us imatrix conversational

Related

Total size
908 GB
Files
33
Quantizations
8
Registered
2026-08-22 13:56
Last updated on HF
2024-06-07 15:12

Files by quantization

Q5_K 2 files 91.8 GB
Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q5_K_M.gguf 46.5 GB 96a67860 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q5_K_S.gguf 45.3 GB 959eceda download
Q4_K 2 files 77.2 GB
Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q4_K_M.gguf 39.6 GB f59451a7 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q4_K_S.gguf 37.6 GB 0583ae6c download
IQ4 1 file 35.3 GB
Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ4_XS.gguf 35.3 GB 19affdfd download
Q3_K 3 files 95.3 GB
Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q3_K_L.gguf 34.6 GB b5efc495 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q3_K_M.gguf 31.9 GB 25553e48 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q3_K_S.gguf 28.8 GB 2aa88e3b download
IQ3 4 files 111 GB
Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ3_M.gguf 29.7 GB 9e79f91c download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ3_S.gguf 28.8 GB c583fef7 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ3_XS.gguf 27.3 GB 1e8fead6 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ3_XXS.gguf 25.6 GB a32456dc download
IQ2 4 files 80.7 GB
Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ2_M.gguf 22.5 GB 5b6a41d5 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ2_S.gguf 20.7 GB 890f4260 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ2_XS.gguf 19.7 GB fcd39dd6 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ2_XXS.gguf 17.8 GB 71637f19 download
IQ1 2 files 29.9 GB
Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ1_M.gguf 15.6 GB cda47996 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.IQ1_S.gguf 14.3 GB 4e43c88e download
Auxiliary files 15 files 387 GB
Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q6_K-split-00001-of-00002.gguf 46.4 GB 93db909e download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.F32-split-00002-of-00006.gguf 46.4 GB faa10bf2 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.F32-split-00004-of-00006.gguf 46.4 GB 981267d7 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q8_0-split-00001-of-00002.gguf 46.3 GB a88183a0 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.F32-split-00001-of-00006.gguf 46.1 GB 5b703c08 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.F32-split-00003-of-00006.gguf 46.1 GB e78d1434 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.F32-split-00005-of-00006.gguf 46.1 GB 14849233 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.F32-split-00006-of-00006.gguf 31.9 GB a474cb74 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q8_0-split-00002-of-00002.gguf 23.5 GB 363ad603 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.Q6_K-split-00002-of-00002.gguf 7.49 GB 91bd52d0 download
Llama-3-70b-Uncensored-Lumi-Tess-gradient.imatrix 23.8 MB 547df978 download
BackyardAI_Logo.png 18.3 KB baa62435 download
BackyardAI_Banner.png 15.0 KB 89f419a7 download
.gitattributes 4.20 KB d6decfcb download
README.md 2.64 KB 0e04d54e download

README current version from Hugging Face


tags:

  • uncencored
  • llama-3
  • tess
  • lumimaid
  • Lumi-tess
    base_model: ryzen88/Llama-3-70b-Uncensored-Lumi-Tess-gradient
    model_name: Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUF
    quantized_by: brooketh
    parameter_count: 70553706496

Backyard.ai

The official library of GGUF format models for use in the local AI chat app, Backyard AI.

Download Backyard AI here to get started.

Request Additional models at r/LLM_Quants.


Llama 3 Uncensored Lumi Tess Gradient 70B

  • Creator: ryzen88
  • Original: Llama 3 Uncensored Lumi Tess Gradient 70B
  • Date Created: 2024-05-10
  • Trained Context: 262144 tokens
  • Description: Good Llama3 uncensored model with a long context, made using a breadcrumb ties merger of Instruct-gradient, Lumimaid, and Tess models. Works with a very wide range of sampler settings.

What is a GGUF?

GGUF is a large language model (LLM) format that can be split between CPU and GPU. GGUFs are compatible with applications based on llama.cpp, such as Backyard AI. Where other model formats require higher end GPUs with ample VRAM, GGUFs can be efficiently run on a wider variety of hardware.
GGUF models are quantized to reduce resource usage, with a tradeoff of reduced coherence at lower quantizations. Quantization reduces the precision of the model weights by changing the number of bits used for each weight.


Backyard.ai

Backyard AI

  • Free, local AI chat application.
  • One-click installation on Mac and PC.
  • Automatically use GPU for maximum speed.
  • Built-in model manager.
  • High-quality character hub.
  • Zero-config desktop-to-mobile tethering.
    Backyard AI makes it easy to start chatting with AI using your own characters or one of the many found in the built-in character hub. The model manager helps you find the latest and greatest models without worrying about whether it's the correct format. Backyard AI supports advanced features such as lorebooks, author's note, text formatting, custom context size, sampler settings, grammars, local TTS, cloud inference, and tethering, all implemented in a way that is straightforward and reliable.
    Join us on Discord

README history 1 version

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

  1. 2024-06-07Upload Llama-3-70b-Uncensored-Lumi-Tess-gradient-GGUFb47458f2.6 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.

Open in Abliteration