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

darkmaniac7/Qwen3.5-0.8B-uncensored-MNN

darkmaniac7 Qwen 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/darkmaniac7%2FQwen3.5-0.8B-uncensored-MNN"
Response includes
  • classification m1
  • files 11
  • hub_downloads_all_time 2,930
  • author_summary 21 models
  • readme_text full
Try next
GET/models?author=darkmaniac7
All 21 models by darkmaniac7
 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
3K
2K last 30d - active
Likes
0
Model age
4mo ago
created 2026-06-12
Downloads over time
Now3.6K→from0↑0%
01.3K2.7K4K0 on Jun 103.6K on Oct 11JunJulAugSepOct
Jun 10 → Oct 11 · 57 snapshots · spans 123 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.

huihui-ai/Huihui-Qwen3.5-0.8B-abliterated↓ 976 this lineage
darkmaniac7/Qwen3.5-0.8B-uncensored-MNN↓ 2,008

Metadata

License
apache-2.0
Languages
en
Tags
mnn abliterated uncensored qwen3.5 on-device mobile en base_model:huihui-ai/Huihui-Qwen3.5-0.8B-abliterated base_model:quantized:huihui-ai/Huihui-Qwen3.5-0.8B-abliterated license:apache-2.0 region:us

Related

Other by darkmaniac7
Qwen3.5-4B-uncensored-MNN 2K Qwen3.5-9B-uncensored-MNN 1K Qwen3.5-9B-ultra-uncensored-heretic-v1-MNN 337 Qwen3-4B-abliterated-MNN 234 Qwen3.6-35B-A3B-abliterated-MNN 185
Same base model
mradermacher/Huihui-Qwen3.5-0.8B-abliterated-GGUF 3K mradermacher/Huihui-Qwen3.5-0.8B-abliterated-i1-GGUF 2K bobber/routangseng-qwen35-0.8b-abliterated-gguf 96 nbeerbower/Huihui-Qwen3.5-0.8B-abliterated-Athanorlite-ORPO 21 bobber/routangseng-qwen35-0.8b-abliterated 15
Total size
0 B
Files
11
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-10-05 08:42
Source huggingface.co/darkmaniac7/Qwen3.5-0.8B-uncensored-MNN ↗ Base model huihui-ai/Huihui-Qwen3.5-0.8B-abliterated →

Files by quantization

Auxiliary files 11 files 523 MB
llm.mnn.weight 449 MB 4ce1b103 download
visual.mnn.weight 60.1 MB 4c03fcac download
tokenizer.mtok 7.00 MB 83a89f72 download
llm.mnn.json 5.11 MB b6a4260c download
llm.mnn 2.06 MB f1d53da8 download
visual.mnn 246 KB 7948ebac download
llm_config.json 8.53 KB 87c8babc download
README.md 1.80 KB 253da384 download
.gitattributes 1.72 KB f081f536 download
export_args.json 1.09 KB 1389ec64 download
config.json 693 B 7804343c download

README current version from Hugging Face

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

  • mnn
  • abliterated
  • uncensored
  • qwen3.5
  • on-device
  • mobile
    language:
  • en
    library_name: mnn

TokForge

Runs on-device in the TokForge app.

Qwen3.5-0.8B Uncensored — MNN Format (mix-mask export)

MNN conversion of huihui-ai/Huihui-Qwen3.5-0.8B-abliterated (vision included) for on-device inference. All credit for the abliteration goes to huihui-ai.

  • Hybrid attention: 18 LinearAttention + 6 full-attention layers of 24 — self-describing metadata (attention_type:"mix", layer_nums:24, sliding_window:4), stacked mask graph [2,1,1,seq,kv]
  • Quantization: 4-bit, block 64, HQQ (matches the taobao-mnn 0.8B bundle parameters)
  • Tokenizer: tokenizer.mtok (new format)
  • Exporter: MNN-TokForge tokforge/rebase-3.5.0 @ 21c339c2fd (upstream #4336 attention-type detection)
  • Requires an MNN runtime with the mix-mask gen_attention_mask path (MNN-TokForge ≥ tokforge/rebase-3.5.0); legacy single-mask runtimes are NOT compatible
  • Validated: multi-turn coherence (3 cycles/session, CPU), LinearAttention snapshot/restore (Y=Z), self-describing hybrid metadata verified against the exported graph

File checksums (md5)

3af7de552fb9cea05e67f615d96efb53  llm.mnn
10fe7c624159f62c69d93a0e836fc80f  llm.mnn.weight
88bbc9851fc9e2aae364eaf59698326a  llm_config.json
3c183b4e10bef80909cb6998fe5e4fa6  tokenizer.mtok
06b782392bdb4ca19a1045c3709fdbb6  visual.mnn
e48e427a48dc363278ecaacb7810db6a  visual.mnn.weight

README history 3 versions

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

  1. 2026-10-05Card metadata: license, base_model, base_model_relation071488b1.8 KB
    Loading...
  2. 2026-07-04Add TokForge app links7ad28021.8 KB
    Loading...
  3. 2026-06-12initial: mix-mask export (attention_type=mix, layer_nums=24) from huihui-ai/H...31e3e021.5 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