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

Apel-sin/qwq-32b-instruct-abliterated-exl2

Apel-sin Qwen 32B 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/Apel-sin%2Fqwq-32b-instruct-abliterated-exl2"
Response includes
  • classification m5
  • files 3
  • hub_downloads_all_time 9
  • author_summary 19 models
  • readme_text full
Try next
GET/models?author=Apel-sin
All 19 models by Apel-sin
 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
9
0
Likes
1
Model age
22mo ago
created 2024-12-11
Downloads over time
Now9→from4↑125%
037104 on Dec 11, 20249 on Oct 119 on Mar 5, 2025Dec '24Mar '25Jun '25Sep '25Dec '25MarJunSep
Dec 11, 2024 → Oct 11 · 135 snapshots · spans 669 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.

zypcastles/QwQ-32B-Instruct-abliterated↓ 21 this lineage
Apel-sin/qwq-32b-instruct-abliterated-exl2

Metadata

Tags
transformers mergekit merge base_model:zypcastles/QwQ-32B-Instruct-abliterated base_model:finetune:zypcastles/QwQ-32B-Instruct-abliterated endpoints_compatible region:us

Related

Other by Apel-sin
llama-3-8B-abliterated-v2-exl2 6 llama-3-NeuralDaredevil-8B-abliterated-exl2 5 qwen2.5-14b-instruct-abliterated-v2-exl2 3 llama-3-8B-abliterated-v3-exl2 2 qwen3-8b-abliterated-mlabonne-exl2 2
Same base model
mradermacher/QwQ-32B-Instruct-abliterated-i1-GGUF 892 mradermacher/QwQ-32B-Instruct-abliterated-GGUF 465
Total size
0 B
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2024-12-11 18:27
Source huggingface.co/Apel-sin/qwq-32b-instruct-abliterated-exl2 ↗ Base model zypcastles/QwQ-32B-Instruct-abliterated →

Files by quantization

Auxiliary files 3 files 3.41 MB
measurement.json 3.41 MB 7b2b8906 download
.gitattributes 1.48 KB a6344aac download
README.md 1.01 KB 37b0a974 download

README current version from Hugging Face

base_model:

  • zypcastles/QwQ-32B-Instruct-abliterated
    library_name: transformers
    tags:
  • mergekit
  • merge

This model is created to fix the instruction-following flaws presented in the QwQ model.

merge

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

Merge Details

Merge Method

This model was merged using the SLERP merge method.

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/QwQ-32B-Preview-abliterated
  - model: huihui-ai/Qwen2.5-32B-Instruct-abliterated
merge_method: slerp
base_model: huihui-ai/QwQ-32B-Preview-abliterated
parameters:
  t: [0.1, 0.2, 0.3, 0.3, 0.2]
dtype: bfloat16

README history 1 version

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

  1. 2024-12-11add measurement.json6ac1b641 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