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

isogen/Josiefied-Qwen3-4B-abliterated-v1-exl3-4bpw

isogen Qwen 1.1B second-order
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/isogen%2FJosiefied-Qwen3-4B-abliterated-v1-exl3-4bpw"
Response includes
  • classification m1
  • files 11
  • benchmarks 11 entries
  • hub_downloads_all_time 70
  • author_summary 14 models
  • readme_text full
Try next
GET/models?author=isogen
All 14 models by isogen
 GET/models?family=qwen&method=m1
Sibling qwen models · same method
 GET/methods/m1
What "m1" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M1
Primary method

Direct removal

No other method signals detected in this model.
Confidence
MEDIUM
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=0 (base model)
  • no specific method indicators - defaulting to M1 (most common)
How we label → About M1 →
Refusal direction extracted via
Extraction technique

Difference-of-means

FromArditi et al. (2024) ↗
Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
What is a refusal direction? → Read the paper ↗
Downloads · lifetime
70
13 last 30d - stable
Likes
0
Model age
17mo ago
created 2025-05-14
Downloads over time
Now78→from1↑7,700%
02957861 on May 14, 202578 on Oct 1178 on Oct 10May '25Aug '25Nov '25FebMayAug
May 14, 2025 → Oct 11 · 113 snapshots · spans 515 days

Benchmarks

Benchmark Score Source
Entertainment 1.2 UGI
Hazardous 1.8 UGI
Natural Intelligence 14.05 UGI
Political lean -19.0% UGI
Sensitive-Info 10.94 UGI
SocPol 0.5 UGI
UGI 33.96 UGI
Willingness (10) 8 UGI
W10-Adherence 9 UGI
W10-Direct 7 UGI
Writing 21.49 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.

Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1↓ 77 this lineage
isogen/Josiefied-Qwen3-4B-abliterated-v1-exl3-4bpw↓ 13

Metadata

Tags
safetensors qwen3 base_model:Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1 base_model:quantized:Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1 4-bit exl3 region:us

Related

Other by isogen
Josiefied-DeepSeek-R1-0528-Qwen3-8B-abliterated-v1-exl3-8bpw-h8 75 Josiefied-Qwen3-8B-abliterated-v1-exl3-4bpw 43 Josiefied-Qwen3-14B-abliterated-v3-exl3-6bpw 26 Josiefied-Qwen3-14B-abliterated-v3-exl3-4bpw 24 Josiefied-Qwen3-8B-abliterated-v1-exl3-8bpw-h8 20
Same base model
mlx-community/Josiefied-Qwen3-4B-abliterated-v1-4bit 4K mradermacher/Josiefied-Qwen3-4B-abliterated-v1-i1-GGUF 808 mradermacher/Josiefied-Qwen3-4B-abliterated-v1-GGUF 733 Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1-gguf 384 mlx-community/Josiefied-Qwen3-4B-abliterated-v1-6bit 86
Total size
2.69 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-05-14 02:01
Source huggingface.co/isogen/Josiefied-Qwen3-4B-abliterated-v1-exl3-4bpw ↗ Base model Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1 →

Files by quantization

Auxiliary files 11 files 2.71 GB
model.safetensors 2.69 GB 66e37439 download
tokenizer.json 10.9 MB aeb13307 download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
tokenizer_config.json 9.48 KB 7345216a download
README.md 1.56 KB 536330a4 download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.02 KB b7eda740 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
generation_config.json 214 B e4f1d319 download

README current version from Hugging Face

base_model: Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v1

EXL3 quantization of Josiefied-Qwen3-4B-abliterated-v1, 4 bits per weight.

HumanEval (argmax)

Model Q4 Q6 Q8 FP16
Josiefied-Qwen3-4B-abliterated-v1-exl3-4bpw 79.3% 78.7% 78.7% 80.5%
Josiefied-Qwen3-4B-abliterated-v1-exl3-6bpw 79.3% 78.0% 78.7% 78.7%
Josiefied-Qwen3-4B-abliterated-v1-exl3-8bpw-h8 79.3% 78.0% 76.8% 78.0%
Qwen3-4B-exl3-4bpw 80.5% 81.1% 81.7% 80.5%
Qwen3-4B-exl3-6bpw 80.5% 85.4% 86.0% 86.0%
Qwen3-4B-exl3-8bpw-h8 82.3% 84.8% 83.5% 82.9%

README history 1 version

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

  1. 2025-05-14Upload folder using huggingface_hub2b9f8a51.6 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.

Get the app Browse the catalog
Open in Abliteration