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

bunnycore/Qwen3-1.7B-abliterated-lora

bunnycore Qwen 1.7B
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-abliterated-lora"
Response includes
  • classification m5
  • files 4
  • benchmarks 11 entries
  • hub_downloads_all_time 52
  • 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
52
29 last 30d - active
Likes
1
Descendants
4
in 1 direct fork
Model age
14mo ago
created 2025-07-20
Downloads over time
Now54→from7↑671%
02040597 on Jul 23, 202554 on Oct 11Jul '25Sep '25Nov '25JanMarMayJulSep
Jul 23, 2025 → Oct 11 · 103 snapshots · spans 445 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 1.4 UGI
Hazardous 1.2 UGI
Natural Intelligence 12.04 UGI
Political lean -19.8% UGI
Sensitive-Info 12.95 UGI
SocPol 1.2 UGI
UGI 33.63 UGI
Willingness (10) 7.5 UGI
W10-Adherence 9 UGI
W10-Direct 6 UGI
Writing 18.77 UGI

Genealogy 1 direct fork

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/Qwen3-1.7B this lineage
bunnycore/Qwen3-1.7B-abliterated-lora↓ 29 1 fork
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

Tags
peft safetensors mergekit base_model:Qwen/Qwen3-1.7B base_model:adapter:Qwen/Qwen3-1.7B 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-Nyx-abliterated 15 Qwen3-4B-abliterated-lora 9
Same base model
huihui-ai/Huihui-Qwen3-1.7B-abliterated-v2 2K mlabonne/Qwen3-1.7B-abliterated 999 UnfilteredAI/DAN-Qwen3-1.7B 657 ElementMerc/qwen3-1.7b-abliterated 266 ops-malware/qwen3-1.7b-abliterated 255
Total size
2.58 GB
Files
4
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2025-07-20 20:40
Source huggingface.co/bunnycore/Qwen3-1.7B-abliterated-lora ↗ Base model Qwen/Qwen3-1.7B ↗

Files by quantization

Auxiliary files 4 files 2.58 GB
adapter_model.safetensors 2.58 GB a580161d download
.gitattributes 1.48 KB a6344aac download
README.md 726 B 67d2ae42 download
adapter_config.json 650 B f4e79138 download

README current version from Hugging Face

base_model:

  • Qwen/Qwen3-1.7B
  • mlabonne/Qwen3-1.7B-abliterated
    library_name: peft
    tags:
  • mergekit
  • peft

output_path

This is a LoRA extracted from a language model. It was extracted using mergekit.

LoRA Details

This LoRA adapter was extracted from mlabonne/Qwen3-1.7B-abliterated and uses Qwen/Qwen3-1.7B as a base.

Parameters

The following command was used to extract this LoRA adapter:

/usr/local/bin/mergekit-extract-lora --model mlabonne/Qwen3-1.7B-abliterated --base-model Qwen/Qwen3-1.7B --out-path output_path --no-lazy-unpickle --max-rank=64

README history 1 version

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

  1. 2025-07-20Upload folder using huggingface_hubcc3d51b726 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