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

nbeerbower/Qwen3-4B-abliterated-TIES

nbeerbower Qwen 4.0B
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/nbeerbower%2FQwen3-4B-abliterated-TIES"
Response includes
  • classification m5
  • files 13
  • hub_downloads_all_time 383
  • author_summary 27 models
  • readme_text full
Try next
GET/models?author=nbeerbower
All 27 models by nbeerbower
 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
383
27 last 30d - cooling
Likes
1
Descendants
2
in 2 direct forks
Model age
17mo ago
created 2025-05-02
Downloads over time
Now393→from2↑19,550%
01442884322 on Apr 30, 2025393 on Oct 11393 on Oct 9Apr '25Jul '25Oct '25JanAprJulOct
Apr 30, 2025 → Oct 11 · 115 snapshots · spans 529 days

Genealogy 2 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/Qwen3-4B-Base this lineage
nbeerbower/Qwen3-4B-abliterated-TIES↓ 27 2 forks
mradermacher/Qwen3-4B-abliterated-TIES-i1-GGUF↓ 490
mradermacher/Qwen3-4B-abliterated-TIES-GGUF↓ 191

Metadata

License
apache-2.0
Tags
transformers safetensors qwen3 text-generation mergekit merge conversational arxiv:2306.01708 base_model:Qwen/Qwen3-4B-Base base_model:merge:Qwen/Qwen3-4B-Base base_model:huihui-ai/Qwen3-4B-abliterated base_model:merge:huihui-ai/Qwen3-4B-abliterated

Related

Other by nbeerbower
Huihui-Qwen3.5-27B-abliterated-Athanorlite-ORPO-v2-GGUF 191 llama-3-spicy-abliterated-stella-8B 46 EVA-abliterated-Qwen2.5-7B 46 Huihui-Qwen3.5-9B-abliterated-Grimoire-SimPO 46 Qwen3-8B-abliterated-TIES 45
Same base model
IIEleven11/Qwen3-4B-abliterated_dark 16
Total size
7.49 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-05-04 00:35
Source huggingface.co/nbeerbower/Qwen3-4B-abliterated-TIES ↗ Base model Qwen/Qwen3-4B-Base ↗

Files by quantization

Auxiliary files 13 files 7.51 GB
model-00001-of-00002.safetensors 4.65 GB 7cf5b393 download
model-00002-of-00002.safetensors 2.84 GB 80e999f5 download
tokenizer.json 10.9 MB aeb13307 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 30.5 KB 7d3c2239 download
tokenizer_config.json 9.48 KB 7345216a download
.gitattributes 1.53 KB 52373fe2 download
README.md 982 B bfa679bd download
config.json 727 B 8c3f4685 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
mergekit_config.yml 239 B 1d886d26 download

README current version from Hugging Face

base_model:

  • Qwen/Qwen3-4B-Base
  • huihui-ai/Qwen3-4B-abliterated
    library_name: transformers
    tags:
  • mergekit
  • merge
    license: apache-2.0

Qwen3-4B-abliterated-TIES

This is a merge of pre-trained language models created using mergekit.

Merge Details

Merge Method

This model was merged using the TIES merge method using Qwen/Qwen3-4B-Base as a base.

Models Merged

The following models were included in the merge:

Configuration

The following YAML configuration was used to produce this model:

models:
  - model: huihui-ai/Qwen3-4B-abliterated
    parameters:
      weight: 1
      density: 1
merge_method: ties
base_model: Qwen/Qwen3-4B-Base
parameters:
  weight: 1
  density: 1
  normalize: true
  int8_mask: true
dtype: bfloat16

README history 2 versions

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

  1. 2025-05-04Update README.mda9d4b82982 B
    Loading...
  2. 2025-05-02Upload folder using huggingface_hubf9cbfab964 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