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

zetasepic/Rombo-LLM-V3.1-QWQ-32b-abliterated

zetasepic Qwen 33B
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/zetasepic%2FRombo-LLM-V3.1-QWQ-32b-abliterated"
Response includes
  • classification m1
  • files 25
  • hub_downloads_all_time 293
  • author_summary 15 models
  • readme_text full
Try next
GET/models?author=zetasepic
All 15 models by zetasepic
 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
293
25 last 30d - cooling
Likes
2
Descendants
3
in 3 direct forks
Model age
19mo ago
created 2025-03-10
Downloads over time
Now307→from64↑380%
5214523833164 on Mar 12, 2025307 on Oct 11Mar '25Jun '25Sep '25Dec '25MarJunSep
Mar 12, 2025 → Oct 11 · 122 snapshots · spans 578 days

Genealogy 3 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.

Qwen/Qwen2.5-32B this lineage
zetasepic/Rombo-LLM-V3.1-QWQ-32b-abliterated↓ 25 3 forks
mradermacher/Rombo-LLM-V3.1-QWQ-32b-abliterated-i1-GGUF↓ 877
mradermacher/Rombo-LLM-V3.1-QWQ-32b-abliterated-GGUF↓ 209
DataSoul/Rombo-LLM-V3.1-QWQ-32b-abliterated-Q5_K_S-GGUF↓ 20

Metadata

License
apache-2.0
Languages
en
Tags
transformers safetensors qwen2 text-generation chat conversational en base_model:Qwen/Qwen2.5-32B base_model:finetune:Qwen/Qwen2.5-32B license:apache-2.0 text-generation-inference endpoints_compatible

Related

Other by zetasepic
Qwen2.5-72B-Instruct-abliterated-GGUF 3K Qwen2.5-32B-Instruct-abliterated-v2-GGUF 2K Qwen2.5-72B-Instruct-abliterated-v2-GGUF 992 Qwen2.5-32B-Instruct-abliterated-v2 119 Qwen2.5-72B-Instruct-abliterated 80
Same base model
CombinHorizon/huihui-ai-abliterated-Qwen2.5-32B-Inst-BaseMerge-TIES 38 CombinHorizon/zetasepic-abliteratedV2-Qwen2.5-32B-Inst-BaseMerge-TIES 36 nbeerbower/QwQ-R1-abliterated-TIES-Qwen2.5-32B 22
Total size
61.0 GB
Files
25
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-03-12 17:37
Source huggingface.co/zetasepic/Rombo-LLM-V3.1-QWQ-32b-abliterated ↗ Base model Qwen/Qwen2.5-32B ↗

Files by quantization

Auxiliary files 25 files 61.0 GB
model-00001-of-00014.safetensors 4.56 GB 09c8921c download
model-00004-of-00014.safetensors 4.54 GB 72a29e5f download
model-00005-of-00014.safetensors 4.54 GB c09c891b download
model-00006-of-00014.safetensors 4.54 GB 80940bb4 download
model-00007-of-00014.safetensors 4.54 GB 343026c4 download
model-00008-of-00014.safetensors 4.54 GB e9cf923c download
model-00009-of-00014.safetensors 4.54 GB be12f173 download
model-00010-of-00014.safetensors 4.54 GB afa9edcf download
model-00011-of-00014.safetensors 4.54 GB 8fcfb942 download
model-00012-of-00014.safetensors 4.54 GB 6c83f6e1 download
model-00013-of-00014.safetensors 4.54 GB 396fb031 download
model-00003-of-00014.safetensors 4.54 GB 113a86a3 download
model-00002-of-00014.safetensors 4.54 GB ff1a9514 download
model-00014-of-00014.safetensors 1.98 GB bc6b1e69 download
tokenizer.json 6.71 MB c6f328af download
vocab.json 2.65 MB 4783fe10 download
merges.txt 1.59 MB 31349551 download
model.safetensors.index.json 61.8 KB 5001e730 download
tokenizer_config.json 7.89 KB bec9032c download
.gitattributes 1.48 KB a6344aac download
README.md 794 B dc68f304 download
config.json 720 B 04fbe62a download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
generation_config.json 214 B ab6cc386 download

README current version from Hugging Face

license: apache-2.0
license_link: https://huggingface.co/Qwen/QWQ-32B/blob/main/LICENSE
language:

  • en
    pipeline_tag: text-generation
    base_model: Qwen/Qwen2.5-32B
    tags:
  • chat
    library_name: transformers

Abliterated version of Rombo-Org/Rombo-LLM-V3.1-QWQ-32b, utilizing code from refusal_direction.

For more information about the Abliterated technique, refer to this article and check out @FailSpy.

GGUF

This model is licensed under the Qwen LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved.

README history 1 version

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

  1. 2025-03-12Create README.md0165a7e794 B
    Loading...

Discussions 1 thread

  1. 2025-04-27PRImprove language tagopen1 💬#1
    Loading...

Continue on Hugging Face →

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