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

isogen/Josiefied-Qwen3-8B-abliterated-v1-exl3-8bpw-h8

isogen Qwen 3.8B 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-Qwen3-8B-abliterated-v1-exl3-8bpw-h8"
Response includes
  • classification m1
  • files 13
  • benchmarks 11 entries
  • hub_downloads_all_time 107
  • 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
107
20 last 30d - stable
Likes
0
Model age
17mo ago
created 2025-05-11
Downloads over time
Now114→from2↑5,600%
042831252 on May 7, 2025114 on Oct 11114 on Oct 10May '25Aug '25Nov '25FebMayAug
May 7, 2025 → Oct 11 · 114 snapshots · spans 522 days

Benchmarks

Benchmark Score Source
Entertainment 1 UGI
Hazardous 2.4 UGI
Natural Intelligence 16.98 UGI
Political lean -18.2% UGI
Sensitive-Info 16.78 UGI
SocPol 1.9 UGI
UGI 40.36 UGI
Willingness (10) 8.8 UGI
W10-Adherence 8.5 UGI
W10-Direct 9 UGI
Writing 23.38 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-Qwen3-8B-abliterated-v1↓ 1,573 this lineage
isogen/Josiefied-Qwen3-8B-abliterated-v1-exl3-8bpw-h8↓ 20

Metadata

Tags
safetensors qwen3 base_model:Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 base_model:quantized:Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 8-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-Qwen3-4B-abliterated-v2-exl3-4bpw 18
Same base model
DavidAU/Qwen3-8B-64k-Context-2X-Josiefied-Uncensored 240K bartowski/Goekdeniz-Guelmez_Josiefied-Qwen3-8B-abliterated-v1-GGUF 7K mradermacher/Josiefied-Qwen3-8B-abliterated-v1-GGUF 4K mlx-community/Josiefied-Qwen3-8B-abliterated-v1-4bit 3K mradermacher/Josiefied-Qwen3-8B-abliterated-v1-i1-GGUF 1K
Total size
8.21 GB
Files
13
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-05-12 14:03
Source huggingface.co/isogen/Josiefied-Qwen3-8B-abliterated-v1-exl3-8bpw-h8 ↗ Base model Goekdeniz-Guelmez/Josiefied-Qwen3-8B-abliterated-v1 →

Files by quantization

Auxiliary files 13 files 8.23 GB
model-00001-of-00002.safetensors 7.63 GB c8f8aa12 download
model-00002-of-00002.safetensors 594 MB e739aca5 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 74.5 KB 77db28d5 download
tokenizer_config.json 9.48 KB 7345216a download
README.md 1.56 KB c7d7bfdc download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.02 KB 715cef4c 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-Qwen3-8B-abliterated-v1

EXL3 quantization of Josiefied-Qwen3-8B-abliterated-v1, 8 bits per weight, including output layers.

HumanEval (argmax)

Model Q4 Q6 Q8 FP16
Josiefied-Qwen3-8B-abliterated-v1-exl3-4bpw 84.1 85.4 86.0 85.4
Josiefied-Qwen3-8B-abliterated-v1-exl3-6bpw 86.6 85.4 86.0 85.4
Josiefied-Qwen3-8B-abliterated-v1-exl3-8bpw-h8 85.4 86.6 85.4 86.6
Qwen3-8B-exl3-4bpw 86.0 85.4 86.0 87.2
Qwen3-8B-exl3-6bpw 84.8 86.0 87.2 87.2
Qwen3-8B-exl3-8bpw-h8 86.0 87.2 86.6 86.6

README history 3 versions

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

  1. 2025-05-12Update README.mde5042ad1.6 KB
    Loading...
  2. 2025-05-11Update README.mdcf3caef1.6 KB
    Loading...
  3. 2025-05-11Upload folder using huggingface_hub46fcf541.5 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