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

beyoru/Luna-SRSA-Uncensored-gguf

beyoru Qwen 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/beyoru%2FLuna-SRSA-Uncensored-gguf"
Response includes
  • classification m8
  • files 3
  • hub_downloads_all_time 504
  • author_summary 2 models
  • readme_text full
Try next
GET/models?author=beyoru
All 2 models by beyoru
 GET/models?family=qwen&method=m8
Sibling qwen 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)

Applied on top of direct removal inherited from the base model.
Confidence
MEDIUM
Inherited from base model
M1 Direct removal →
Why this label 3 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.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
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
504
34 last 30d - cooling
Likes
2
Model age
6mo ago
created 2026-04-02
Downloads over time
Now518→from292↑77%
281367454541292 on Apr 15518 on Oct 11518 on Oct 8AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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.

beyoru/Luna-SRSA-Uncensored↓ 49 this lineage
beyoru/Luna-SRSA-Uncensored-gguf↓ 34

Variants by this author 2 formats · 83 downloads combined

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

Metadata

License
mit
Quantizations
Q8_0
Tags
transformers gguf uncensored srsa abliterated roleplay qwen3 base_model:beyoru/Luna-SRSA-Uncensored base_model:quantized:beyoru/Luna-SRSA-Uncensored license:mit endpoints_compatible region:us

Related

Other by beyoru
Luna-SRSA-Uncensored 49
Same base model
mradermacher/Luna-SRSA-Uncensored-i1-GGUF 603 mradermacher/Luna-SRSA-Uncensored-GGUF 305
Total size
3.99 GB
Files
3
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2026-04-28 10:42
Source huggingface.co/beyoru/Luna-SRSA-Uncensored-gguf ↗ Base model beyoru/Luna-SRSA-Uncensored →

Files by quantization

Q8_0 1 file 3.99 GB
Luna-SRSA-Uncensored.Q8_0.gguf 3.99 GB c8221bcf download
Auxiliary files 2 files 2.52 KB
.gitattributes 1.55 KB 3bc4e79d download
README.md 993 B 5340dd2c download

README current version from Hugging Face

license: mit
tags:

  • uncensored
  • srsa
  • abliterated
  • roleplay
  • qwen3
  • gguf
    library_name: transformers
    base_model:
  • beyoru/Luna-SRSA-Uncensored

Luna-SRSA-Uncensored

Uncensored version of beyoru/Luna via SRSA (Spectral Refusal Subspace Ablation).

GitHub
HuggingFace
BMC

Stats

This is a exp model

Luna is a conversational AI model designed for immersive roleplay (RP) and natural chatting.
It is fine-tuned to respond in a more engaging, character-driven style compared to standard instruction-tuned models.

Evaluate

Might don't have in near future

README history 3 versions

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

  1. 2026-04-28Update README.md67f3a46993 B
    Loading...
  2. 2026-04-02Update README.md4db8a8d685 B
    Loading...
  3. 2026-04-02Create README.mdc43d148643 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