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

bunnycore/Qwen3-1.7B-Nyx-abliterated

bunnycore 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/bunnycore%2FQwen3-1.7B-Nyx-abliterated"
Response includes
  • classification m5
  • files 17
  • hub_downloads_all_time 99
  • author_summary 9 models
  • readme_text full
Try next
GET/models?author=bunnycore
All 9 models by bunnycore
 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
99
15 last 30d - stable
Likes
3
Descendants
3
in 3 direct forks
Model age
14mo ago
created 2025-07-20
Downloads over time
Now106→from34↑212%
30588611334 on Jul 23, 2025106 on Oct 11Jul '25Sep '25Nov '25JanMarMayJulSep
Jul 23, 2025 → Oct 11 · 103 snapshots · spans 445 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.

bunnycore/Qwen3-1.7B-abliterated-lora↓ 29 this lineage
bunnycore/Qwen3-1.7B-Nyx-abliterated↓ 15 3 forks
mradermacher/Qwen3-1.7B-Nyx-abliterated-i1-GGUF↓ 680
mradermacher/Qwen3-1.7B-Nyx-abliterated-GGUF↓ 363
Novaciano/Qwen3-1.7B-Nyx-abliterated-Q4_K_M-GGUF↓ 26

Metadata

License
apache-2.0
Tags
safetensors qwen3 merge mergekit lazymergekit base_model:bunnycore/Qwen3-1.7B-Nyx-V3 base_model:merge:bunnycore/Qwen3-1.7B-Nyx-V3 base_model:bunnycore/Qwen3-1.7B-abliterated-lora base_model:merge:bunnycore/Qwen3-1.7B-abliterated-lora license:apache-2.0 region:us

Related

Other by bunnycore
kappa-3-phi-abliterated-Q5_K_M-GGUF 50 Huihui-granite-4.0-h-micro-abliterated-Q5_K_M-GGUF 43 LLama-3.1-8B-HyperNova-abliteration 31 Qwen3-1.7B-abliterated-lora 29 Qwen3-4B-abliterated-lora 9
Total size
3.78 GB
Files
17
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-07-21 19:38
Source huggingface.co/bunnycore/Qwen3-1.7B-Nyx-abliterated ↗ Base model bunnycore/Qwen3-1.7B-abliterated-lora →

Files by quantization

Auxiliary files 17 files 3.80 GB
model-00002-of-00005.safetensors 954 MB 2695dee8 download
model-00004-of-00005.safetensors 936 MB d5a8039d download
model-00003-of-00005.safetensors 936 MB 87b6c3c0 download
model-00001-of-00005.safetensors 594 MB 912becff download
model-00005-of-00005.safetensors 456 MB 17d19085 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 23.8 KB 54227dc5 download
tokenizer_config.json 5.28 KB ddaf6980 download
chat_template.jinja 4.02 KB 699ff8df download
.gitattributes 1.53 KB 52373fe2 download
config.json 1.33 KB 7f8bc1dd download
README.md 1.06 KB a0a96787 download
added_tokens.json 707 B b54f9135 download
special_tokens_map.json 613 B ac23c0aa download
mergekit_config.yml 192 B 21f5f683 download

README current version from Hugging Face

license: apache-2.0
tags:

  • merge
  • mergekit
  • lazymergekit
    base_model:
  • bunnycore/Qwen3-1.7B-abliterated-lora
  • bunnycore/Qwen3-1.7B-Nyx-V3

Qwen3-1.7B-abliterated

Intended Use

This model is intended for research and experimental purposes, particularly in scenarios requiring a language model with fewer inherent safety filters. Specific use cases include:

  • General Text Generation: Producing human-like text for various prompts.
  • Role-Playing Scenarios: Engaging in character-based conversations and narratives.
  • Exploration of Unfiltered Content Generation: Investigating the capabilities and behaviors of language models with reduced censorship.
  • Mobile Device Friendly
  • Reasoning Capabilities: Capable of performing certain reasoning tasks, allowing for more complex problem-solving and logical deduction in generated responses.

🧩 Configuration


base_model: bunnycore/Qwen3-1.7B-Nyx-V3+bunnycore/Qwen3-1.7B-abl-Lora
dtype: bfloat16
merge_method: passthrough
models:
  - model: bunnycore/Qwen3-1.7B-Nyx-V3+bunnycore/Qwen3-1.7B-abl-Lora

README history 4 versions

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

  1. 2025-07-21Update README.mdc360ca31.1 KB
    Loading...
  2. 2025-07-21Update README.md8ce8ecf1.2 KB
    Loading...
  3. 2025-07-21Update README.md19508fa514 B
    Loading...
  4. 2025-07-20Upload folder using huggingface_hub087830b432 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