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

bartowski/Lexi-Llama-3-8B-Uncensored-exl2

bartowski Llama 8B
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/bartowski%2FLexi-Llama-3-8B-Uncensored-exl2"
Response includes
  • classification m-uncensored
  • files 3
  • hub_downloads_all_time 45
  • author_summary 72 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
45
13 last 30d - stable
Likes
3
Model age
2.5y ago
created 2024-04-24
Downloads over time
Now52→from8↑550%
0801602408 on Jul 24, 202452 on Oct 11218 on Jan 7Jul '24Nov '24Mar '25Jul '25Nov '25MarJul
Jul 24, 2024 → Oct 11 · 155 snapshots · spans 809 days

Variants by this author 2 formats · 10K downloads combined

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

Metadata

License
llama3
Tags
uncensored llama3 instruct open text-generation license:llama3 region:us

Related

Total size
0 B
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-04-24 03:03

Files by quantization

Auxiliary files 3 files 1.71 MB
measurement.json 1.70 MB ea05d99c download
README.md 3.06 KB 521c6a67 download
.gitattributes 1.48 KB a6344aac download

README current version from Hugging Face


license: llama3
tags:

  • uncensored
  • llama3
  • instruct
  • open
    quantized_by: bartowski
    pipeline_tag: text-generation

Exllama v2 Quantizations of Lexi-Llama-3-8B-Uncensored

If generation refuses to stop, you can edit tokenizer_config.json.

Replace line 2055:

"eos_token": "<|end_of_text|>",

with:

"eos_token": "<|eot_id|>",

Using turboderp's ExLlamaV2 v0.0.19 for quantization.

The "main" branch only contains the measurement.json, download one of the other branches for the model (see below)

Each branch contains an individual bits per weight, with the main one containing only the meaurement.json for further conversions.

Original model: https://huggingface.co/Orenguteng/Lexi-Llama-3-8B-Uncensored

Prompt format

<|begin_of_text|><|start_header_id|>system<|end_header_id|>

{system_prompt}<|eot_id|><|start_header_id|>user<|end_header_id|>

{prompt}<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Available sizes

Branch Bits lm_head bits VRAM (4k) VRAM (8K) VRAM (16k) VRAM (32k) Description
8_0 8.0 8.0 10.1 GB 10.5 GB 11.5 GB 13.6 GB Maximum quality that ExLlamaV2 can produce, near unquantized performance.
6_5 6.5 8.0 8.9 GB 9.3 GB 10.3 GB 12.4 GB Very similar to 8.0, good tradeoff of size vs performance, recommended.
5_0 5.0 6.0 7.7 GB 8.1 GB 9.1 GB 11.2 GB Slightly lower quality vs 6.5, but usable on 8GB cards.
4_25 4.25 6.0 7.0 GB 7.4 GB 8.4 GB 10.5 GB GPTQ equivalent bits per weight, slightly higher quality.
3_5 3.5 6.0 6.4 GB 6.8 GB 7.8 GB 9.9 GB Lower quality, only use if you have to.

Download instructions

With git:

git clone --single-branch --branch 6_5 https://huggingface.co/bartowski/Lexi-Llama-3-8B-Uncensored-exl2 Lexi-Llama-3-8B-Uncensored-exl2-6_5

With huggingface hub (credit to TheBloke for instructions):

pip3 install huggingface-hub

To download a specific branch, use the --revision parameter. For example, to download the 6.5 bpw branch:

Linux:

huggingface-cli download bartowski/Lexi-Llama-3-8B-Uncensored-exl2 --revision 6_5 --local-dir Lexi-Llama-3-8B-Uncensored-exl2-6_5 --local-dir-use-symlinks False

Windows (which apparently doesn't like _ in folders sometimes?):

huggingface-cli download bartowski/Lexi-Llama-3-8B-Uncensored-exl2 --revision 6_5 --local-dir Lexi-Llama-3-8B-Uncensored-exl2-6.5 --local-dir-use-symlinks False

Want to support my work? Visit my ko-fi page here: https://ko-fi.com/bartowski

README history 6 versions

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

  1. 2024-04-24Quant for 3.5bdcdd75812 B
    Loading...
  2. 2024-04-24Quant for 4.2518b580c812 B
    Loading...
  3. 2024-04-24Quant for 5.0ef8e7e0812 B
    Loading...
  4. 2024-04-24Quant for 6.5f322e47812 B
    Loading...
  5. 2024-04-24Quant for 8.0add15db812 B
    Loading...
  6. 2024-04-24measurement.json51b24293.1 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.

Open in Abliteration