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

mradermacher/Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored-GGUF

mradermacher Qwen 7B GGUF MoE second-order 41K 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/mradermacher%2FQwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored-GGUF"
Response includes
  • classification m8
  • files 14
  • hub_downloads_all_time 9,088
  • author_summary 3324 models
  • readme_text full
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
Why this label 3 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • author=mradermacher (M8 quantization producer, never originator)
  • is_gguf=1
  • base_model='DavidAU/Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored' (base has 'abliterated' marker, assume M1 default)
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
9K
496 last 30d - cooling
Likes
3
Model age
13mo ago
created 2025-08-27
Downloads over time
Now9.3K→from357↑2,498%
03.4K6.8K10.2K357 on Aug 27, 20259.3K on Oct 11Aug '25Oct '25Dec '25FebAprJunAugOct
Aug 27, 2025 → Oct 11 · 98 snapshots · spans 410 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.

Variants by this author 2 formats · 1K downloads combined

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

Metadata

License
apache-2.0
Languages
en fr zh de
Quantizations
F16 IQ4 Q2_K Q3_K Q4_K Q5_K Q6_K Q8_0
Tags
transformers gguf programming code generation code codeqwen moe coding coder qwen2 chat qwen

Related

Total size
40.8 GB
Files
14
Quantizations
9
Registered
2026-08-22 13:56
Last updated on HF
2025-08-29 08:56

Files by quantization

F16 1 file 9.12 GB
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.f16.gguf 9.12 GB 30eee65b download
Q8_0 1 file 4.85 GB
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.Q8_0.gguf 4.85 GB 2e2343bc download
Q6_K 1 file 3.74 GB
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.Q6_K.gguf 3.74 GB 361807a1 download
Q5_K 2 files 6.45 GB
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.Q5_K_M.gguf 3.27 GB 0c75a930 download
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.Q5_K_S.gguf 3.18 GB 4397505b download
Q4_K 2 files 5.48 GB
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.Q4_K_M.gguf 2.82 GB 6ce18acd download
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.Q4_K_S.gguf 2.66 GB 32554e58 download
IQ4 1 file 2.53 GB
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.IQ4_XS.gguf 2.53 GB 6e357577 download
Q3_K 3 files 6.82 GB
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.Q3_K_L.gguf 2.46 GB d66d876a download
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.Q3_K_M.gguf 2.28 GB 2d6043aa download
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.Q3_K_S.gguf 2.08 GB 5dab9d59 download
Q2_K 1 file 1.79 GB
Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored.Q2_K.gguf 1.79 GB 4f989438 download
Auxiliary files 2 files 7.09 KB
README.md 4.54 KB c6c62ba8 download
.gitattributes 2.55 KB 2481de14 download

README current version from Hugging Face


base_model: DavidAU/Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored
language:

  • en
  • fr
  • zh
  • de
    library_name: transformers
    license: apache-2.0
    mradermacher:
    readme_rev: 1
    quantized_by: mradermacher
    tags:
  • programming
  • code generation
  • code
  • codeqwen
  • programming
  • code generation
  • code
  • codeqwen
  • moe
  • coding
  • coder
  • qwen2
  • chat
  • qwen
  • qwen-coder
  • chat
  • qwen
  • qwen-coder
  • moe
  • mixture of experts
  • 6 experts
  • 2 active experts
  • 40k context
  • qwen3
  • finetune
  • qwen3_moe
  • creative
  • all use cases
  • roleplay
  • merge
  • not-for-all-audiences

About

static quants of https://huggingface.co/DavidAU/Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-Uncensored

For a convenient overview and download list, visit our model page for this model.

weighted/imatrix quants are available at https://huggingface.co/mradermacher/Qwen3-MOE-4x1.7B-6.8B-Lucys-Song-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
GGUF Q2_K 2.0
GGUF Q3_K_S 2.3
GGUF Q3_K_M 2.5 lower quality
GGUF Q3_K_L 2.7
GGUF IQ4_XS 2.8
GGUF Q4_K_S 3.0 fast, recommended
GGUF Q4_K_M 3.1 fast, recommended
GGUF Q5_K_S 3.5
GGUF Q5_K_M 3.6
GGUF Q6_K 4.1 very good quality
GGUF Q8_0 5.3 fast, best quality
GGUF f16 9.9 16 bpw, overkill

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. 2025-08-29auto-patch README.md6ec13504.5 KB
    Loading...
  2. 2025-08-28auto-patch README.md19853614.6 KB
    Loading...
  3. 2025-08-27uploaded from marco7e5a085393 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.

Open in Abliteration