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

roleplaiapp/QwQ-32B-Preview-abliterated-IQ4_XS-GGUF

roleplaiapp Qwen 32B GGUF 33K ctx
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/roleplaiapp%2FQwQ-32B-Preview-abliterated-IQ4_XS-GGUF"
Response includes
  • classification m8
  • files 3
  • hub_downloads_all_time 87
  • author_summary 65 models
  • readme_text full
Try next
GET/models?author=roleplaiapp
All 65 models by roleplaiapp
 GET/models?family=qwen&method=m8
Sibling qwen models · same method
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

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.
  • 'abliterated' in name/tags
  • is_gguf=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
How we label → About M8 →
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
87
44 last 30d - active
Likes
0
Model age
20mo ago
created 2025-01-27
Downloads over time
Now109→from0↑0%
02615227830 on Jan 22, 2025109 on Oct 11712 on Sep 17, 2025Jan '25Apr '25Jul '25Oct '25JanAprJulOct
Jan 22, 2025 → Oct 11 · 129 snapshots · spans 627 days

Variants by this author 3 formats · 123 downloads combined

The same weights this author released in different packaging. Pick the format that matches your runtime.

Metadata

Quantizations
IQ4
Tags
transformers gguf 32b IQ4_XS abliterated iq4 llama-cpp preview qwq text-generation endpoints_compatible region:us

Related

Other by roleplaiapp
Qwen2.5-Coder-14B-Instruct-Uncensored-Q4_K_M-GGUF 3K Qwen2.5-Coder-14B-Instruct-Uncensored-Q5_K_M-GGUF 287 Qwen2.5-7B-Instruct-Uncensored-Q4_K_M-GGUF 233 DeepSeek-R1-Distill-Llama-70B-Uncensored-v2-Q4_K_S-GGUF 229 Llama-3.2-3B-Instruct-uncensored-Q6_K-GGUF 173
Total size
16.6 GB
Files
3
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2025-01-27 12:36
Source huggingface.co/roleplaiapp/QwQ-32B-Preview-abliterated-IQ4_XS-GGUF ↗

Files by quantization

IQ4 1 file 16.6 GB
QwQ-32B-Preview-abliterated.IQ4_XS.gguf 16.6 GB f5a7e8fe download
Auxiliary files 2 files 2.30 KB
.gitattributes 1.56 KB 5db8cb2d download
README.md 763 B e9f491db download

README current version from Hugging Face

library_name: transformers
pipeline_tag: text-generation
tags:

  • 32b
  • IQ4_XS
  • abliterated
  • gguf
  • iq4
  • llama-cpp
  • preview
  • qwq
  • text-generation

roleplaiapp/QwQ-32B-Preview-abliterated-IQ4_XS-GGUF

Repo: roleplaiapp/QwQ-32B-Preview-abliterated-IQ4_XS-GGUF
Original Model: QwQ-32B-Preview-abliterated
Quantized File: QwQ-32B-Preview-abliterated.IQ4_XS.gguf
Quantization: GGUF
Quantization Method: IQ4_XS

Overview

This is a GGUF IQ4_XS quantized version of QwQ-32B-Preview-abliterated

Quantization By

I often have idle GPUs while building/testing for the RP app, so I put them to use quantizing models.
I hope the community finds these quantizations useful.

Andrew Webby @ RolePlai.

README history 1 version

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

  1. 2025-01-27Upload README.md with huggingface_hub9f9c5fe763 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