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

chenrm/qwen3-30b-a3b-abliterated-lora

chenrm Qwen 30B GGUF MoE
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/chenrm%2Fqwen3-30b-a3b-abliterated-lora"
Response includes
  • classification m5
  • files 3
  • benchmarks 16 entries
  • hub_downloads_all_time 475
  • author_summary 9 models
  • readme_text full
Try next
GET/models?author=chenrm
All 9 models by chenrm
 GET/models?family=qwen&method=m5
Sibling qwen models · same method
 GET/methods/m5
What "m5" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M5
Primary method

Mergekit merge

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.
  • merge tag / mergekit / dare-ties in tags or name
  • no unusual architecture pattern (regular merge)
  • abliterated marker present
How we label → About M5 →
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
475
46 last 30d - cooling
Likes
0
Model age
15mo ago
created 2025-06-25
Downloads over time
Now478→from9↑5,211%
01753505259 on Jul 9, 2025478 on Oct 11478 on Oct 7Jul '25Sep '25Nov '25JanMarMayJulSep
Jul 9, 2025 → Oct 11 · 105 snapshots · spans 459 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Arena-Battles 25948 LM-Arena
LM Arena Elo 1321.1938733711484 LM-Arena
Arena-Elo-Lower 1316.3871802173958 LM-Arena
Arena-Elo-Upper 1326.0005665249007 LM-Arena
Arena-Rank 61 LM-Arena
Entertainment 1.2 UGI
Hazardous 2.9 UGI
Natural Intelligence 15.9 UGI
Political lean -26.8% UGI
Sensitive-Info 17.11 UGI
SocPol 1.4 UGI
UGI 33.07 UGI
Willingness (10) 6.5 UGI
W10-Adherence 10 UGI
W10-Direct 3 UGI
Writing 30.24 UGI

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.

Qwen/Qwen3-30B-A3B this lineage
chenrm/qwen3-30b-a3b-abliterated-lora↓ 46

Metadata

Tags
peft safetensors gguf mergekit base_model:Qwen/Qwen3-30B-A3B base_model:adapter:Qwen/Qwen3-30B-A3B region:us

Related

Other by chenrm
qwen3-vl-30b-a3b-instruct-abliterated-h-corpus 124 qwen3.8-flash-next-abliterated-lora 96 qwen2.5-vl-32b-abliterated-h-corpus 59 qwen2.5-14b-deepsex-abliterated-h-corpus 51 qwen3-30b-a3b-abliterated-erotic-lora 28
Same base model
groxaxo/Qwen3.6-35B-A3B-Abliterated-Heretic-GGUF 2K huihui-ai/Qwen3-30B-A3B-abliterated 1K mlabonne/Qwen3-30B-A3B-abliterated 1K Ewere/Qwen3-30B-A3B-abliterated-erotic 251 Goekdeniz-Guelmez/Josiefied-Qwen3-30B-A3B-abliterated-v2 149
Total size
807 MB
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-06-25 02:22
Source huggingface.co/chenrm/qwen3-30b-a3b-abliterated-lora ↗ Base model Qwen/Qwen3-30B-A3B ↗

Files by quantization

Auxiliary files 3 files 807 MB
qwen3-30b-a3b-abliterated-lora.gguf 807 MB c2e5d1ef download
.gitattributes 1.55 KB 21d51362 download
README.md 775 B f17c5bfa download

README current version from Hugging Face

base_model:

  • Qwen/Qwen3-30B-A3B
  • mlabonne/Qwen3-30B-A3B-abliterated
    library_name: peft
    tags:
  • mergekit
  • peft

qwen3-30b-a3b-abliterated-lora

This is a LoRA extracted from a language model. It was extracted using mergekit.

LoRA Details

This LoRA adapter was extracted from mlabonne/Qwen3-30B-A3B-abliterated and uses Qwen/Qwen3-30B-A3B as a base.

Parameters

The following command was used to extract this LoRA adapter:

/venv/main/bin/mergekit-extract-lora --model mlabonne/Qwen3-30B-A3B-abliterated --base-model Qwen/Qwen3-30B-A3B --out-path qwen3-30b-a3b-abliterated-lora --cuda --max-rank 4

README history 1 version

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

  1. 2025-06-25Upload folder using huggingface_hub451b78f775 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