← back to catalog · registered 2026-11-15 13:03

geladons/Huihui-Qwen3.5-0.8B-abliterated

geladons 800M 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/geladons%2FHuihui-Qwen3.5-0.8B-abliterated"
Response includes
  • classification m1
  • files 3
  • author_summary 4 models
  • readme_text full
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)
Refusal direction extracted via
Extraction technique

Difference-of-means

Confidence
MEDIUM
Why we say so
primary_method=M1; difference-of-means is the reference extraction for M1/M3 (Arditi 2024)
Downloads · 30-day
54
Likes
0
Model age
1w ago
created 2026-11-15
Downloads over time
Now 54 → from 0 ↑ 0%
0204059 0 on Nov 15 54 on Nov 22 Nov
Nov 15 → Nov 22 · 8 snapshots · spans 7 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.

Metadata

License
apache-2.0
Tags
litert-lm litertlm litert android on-device edge-ai llm text-generation base_model:huihui-ai/Huihui-Qwen3.5-0.8B-abliterated base_model:finetune:huihui-ai/Huihui-Qwen3.5-0.8B-abliterated license:apache-2.0 region:us

Related

Total size
0 B
Files
3
Quantizations
1
Registered
2026-11-15 13:03
Last updated on HF
2026-11-15 06:51

Files by quantization

Auxiliary files 3 files 919 MB
Huihui-Qwen3.5-0.8B-abliterated_int8_v2.litertlm 919 MB fca0acbb download
README.md 1.80 KB 71f19816 download
.gitattributes 1.57 KB dbda3c83 download

README current version from Hugging Face


license: apache-2.0
base_model: huihui-ai/Huihui-Qwen3.5-0.8B-abliterated
pipeline_tag: text-generation
tags:

  • litertlm
  • litert
  • litert-lm
  • android
  • on-device
  • edge-ai
  • llm
    library_name: litert-lm

Huihui-Qwen3.5-0.8B-abliterated — LiteRT-LM bundle (on-device)

Huihui-Qwen3.5-0.8B-abliterated_int8_v2.litertlm — huihui-ai/Huihui-Qwen3.5-0.8B-abliterated converted to Google's
LiteRT-LM format for fully on-device inference. No cloud, no account:
the model runs entirely on the phone.

Uncensored/abliterated finetune by huihui-ai — fewer refusals than the base instruct model.

Run it

Zero code: install Local AI (free, Google Play) —
this model is in its built-in catalog. Download, tap, chat fully offline.

In your own app: the com.google.ai.edge.litertlm SDK loads this file
directly — point Engine/Conversation at it. Runtime:
https://github.com/google-ai-edge/LiteRT-LM · conversion recipes:
hf-to-litertlm.

Details

Base model huihui-ai/Huihui-Qwen3.5-0.8B-abliterated
Format .litertlm — LiteRT-LM runtime
Quantization int8-quantized
File size 0.96 GB
Modality text → text
License apache-2.0 — same as the base model

The file is byte-identical to the copy in
geladons/local-ai-models, which stays live for backward
compatibility. Per-model repos exist so each bundle has its own card, docs
and download stats.

README history 1 version

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

  1. 2026-11-15 Upload README.md with huggingface_hub f376c7f 1.8 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.

Open in Abliteration