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

bobber/routangseng-qwen35-0.8b-abliterated-onnx

bobber Qwen 800M multimodal 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/bobber%2Froutangseng-qwen35-0.8b-abliterated-onnx"
Response includes
  • classification m1
  • files 9
  • hub_downloads_all_time 691
  • author_summary 5 models
  • readme_text full
Try next
GET/models?author=bobber
All 5 models by bobber
 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
691
22 last 30d - cooling
Likes
0
Model age
7mo ago
created 2026-03-09
Downloads over time
Now696→from532↑31%
524587650712532 on Mar 11696 on Oct 11696 on Oct 6MarAprMayJunJulAugSepOct
Mar 11 → Oct 11 · 70 snapshots · spans 214 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.

bobber/routangseng-qwen35-0.8b-abliterated↓ 15 this lineage
bobber/routangseng-qwen35-0.8b-abliterated-onnx↓ 22

Variants by this author 3 formats · 133 downloads combined

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

Metadata

License
apache-2.0
Languages
zh
Tags
transformers.js onnx qwen3_5 image-text-to-text webgpu qwen3.5 conversational zh base_model:bobber/routangseng-qwen35-0.8b-abliterated base_model:quantized:bobber/routangseng-qwen35-0.8b-abliterated license:apache-2.0 region:us

Related

Other by bobber
routangseng-qwen35-0.8b-abliterated-gguf 96 routangseng-qwen35-0.8b-abliterated-lora-onnx 18 routangseng-qwen35-0.8b-abliterated 15 Huihui-Qwen3.5-0.8B-abliterated-onnx 15
Same base model
mradermacher/routangseng-qwen35-0.8b-abliterated-i1-GGUF 641 mradermacher/routangseng-qwen35-0.8b-abliterated-GGUF 310 bobber/routangseng-qwen35-0.8b-abliterated-lora-onnx 18
Total size
0 B
Files
9
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-03-11 03:44
Source huggingface.co/bobber/routangseng-qwen35-0.8b-abliterated-onnx ↗ Base model bobber/routangseng-qwen35-0.8b-abliterated →

Files by quantization

Auxiliary files 9 files 18.4 MB
tokenizer.json 18.3 MB 89da80cc download
tokenizer_config.json 8.95 KB 9e163a71 download
chat_template.jinja 7.57 KB 0ef09f21 download
config.json 2.89 KB b3345d88 download
.gitattributes 2.12 KB c38d0824 download
processor_config.json 1.27 KB 7ad6acdf download
README.md 1.11 KB c29c88c9 download
preprocessor_config.json 336 B 4ae180b4 download
generation_config.json 248 B 59ee4c19 download

README current version from Hugging Face

license: apache-2.0
language:

  • zh
    tags:
  • onnx
  • webgpu
  • qwen3.5
  • transformers.js
    base_model: bobber/routangseng-qwen35-0.8b-abliterated

routangseng-qwen35-0.8b-abliterated-onnx

ONNX export of bobber/routangseng-qwen35-0.8b-abliterated for browser-side inference with WebGPU via transformers.js.

This is built from the fine-tuned model (identity-override LoRA merged into huihui-ai/Huihui-Qwen3.5-0.8B-abliterated).

Build Process

  1. Source model: bobber/routangseng-qwen35-0.8b-abliterated
  2. ONNX: Weight transplant into reference graph structure from onnx-community/Qwen3.5-0.8B-ONNX
  3. Quantization: q8 (MatMul-only for decoder, full dynamic for embed/vision)

Related

README history 4 versions

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

  1. 2026-03-11Upload README.md with huggingface_hub3f4e6121.1 KB
    Loading...
  2. 2026-03-11Upload README.md with huggingface_hubd0bc65b2.3 KB
    Loading...
  3. 2026-03-10Upload folder using huggingface_hubbfa04ed700 B
    Loading...
  4. 2026-03-09Upload README.md with huggingface_hub020a09a1.5 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