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

isogen/Josiefied-Qwen3-4B-abliterated-v2-exl3-8bpw-h8

isogen Qwen 2.0B 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-v2-exl3-8bpw-h8"
Response includes
  • classification m1
  • files 11
  • hub_downloads_all_time 55
  • author_summary 14 models
  • readme_text full
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · lifetime
55
12 last 30d - stable
Likes
0
Model age
16mo ago
created 2025-05-30
Downloads over time
Now63→from0↑0%
02346690 on May 28, 202563 on Oct 11May '25Aug '25Nov '25FebMayAug
May 28, 2025 → Oct 11 · 111 snapshots · spans 501 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.

Metadata

Tags
safetensors qwen3 base_model:Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v2 base_model:quantized:Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v2 8-bit exl3 region:us

Related

Total size
4.48 GB
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-05-30 22:54

Files by quantization

Auxiliary files 11 files 4.49 GB
model.safetensors 4.48 GB 0f3f3cca 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 9.50 KB c70a754e download
README.md 2.07 KB 2082e188 download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.08 KB 3f446865 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
generation_config.json 237 B 2c927cc5 download

README current version from Hugging Face


base_model: Goekdeniz-Guelmez/Josiefied-Qwen3-4B-abliterated-v2

EXL3 quantization of Josiefied-Qwen3-4B-abliterated-v2, 8 bits per weight, including output layers.

HumanEval (argmax)

Model Q4 Q6 Q8 FP16
Josiefied-Qwen3-4B-abliterated-v2-exl3-4bpw 77.4% 79.3% 78.0% 79.9%
Josiefied-Qwen3-4B-abliterated-v2-exl3-6bpw 77.4% 81.1% 78.0% 79.3%
Josiefied-Qwen3-4B-abliterated-v2-exl3-8bpw-h8 76.8% 82.3% 81.1% 80.5%
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. 2025-05-30Upload folder using huggingface_hube7ccf792.1 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.

Open in Abliteration