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

darkmaniac7/Huihui-gemma-4-E4B-it-abliterated-MNN

darkmaniac7 Gemma 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%2FHuihui-gemma-4-E4B-it-abliterated-MNN"
Response includes
  • classification m1
  • files 14
  • hub_downloads_all_time 498
  • author_summary 21 models
  • readme_text full
Try next
GET/models?author=darkmaniac7
All 21 models by darkmaniac7
 GET/models?family=gemma&method=m1
Sibling gemma 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
498
74 last 30d - stable
Likes
1
Model age
6mo ago
created 2026-04-12
Downloads over time
Now538→from224↑140%
208329449569224 on Apr 15538 on Oct 11538 on Oct 9AprMayJunJulAugSepOct
Apr 15 → Oct 11 · 65 snapshots · spans 179 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-gemma-4-E4B-it-abliterated↓ 2,041 this lineage
darkmaniac7/Huihui-gemma-4-E4B-it-abliterated-MNN↓ 74

Metadata

License
gemma
Tags
mnn mobile tokforge abliterated uncensored gemma-4 base_model:huihui-ai/Huihui-gemma-4-E4B-it-abliterated base_model:quantized:huihui-ai/Huihui-gemma-4-E4B-it-abliterated license:apache-2.0 region:us

Related

Other by darkmaniac7
Qwen3.5-4B-uncensored-MNN 2K Qwen3.5-0.8B-uncensored-MNN 2K Qwen3.5-9B-uncensored-MNN 1K Qwen3.5-9B-ultra-uncensored-heretic-v1-MNN 337 Qwen3-4B-abliterated-MNN 234
Same base model
mradermacher/Huihui-gemma-4-E4B-it-abliterated-GGUF 5K mradermacher/Huihui-gemma-4-E4B-it-abliterated-i1-GGUF 1K EZCon/Huihui-gemma-4-E4B-it-abliterated-4bit-mlx 422 vokash3/Huihui-gemma-4-E4B-it-abliterated-LiteRT-LM 267 lagive/Huihui-gemma-4-E4B-it-abliterated-GGUF 172
Total size
1.64 GB
Files
14
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-10-05 08:42
Source huggingface.co/darkmaniac7/Huihui-gemma-4-E4B-it-abliterated-MNN ↗ Base model huihui-ai/Huihui-gemma-4-E4B-it-abliterated →

Files by quantization

Auxiliary files 14 files 5.13 GB
ple_embeddings_int4.bin 1.64 GB 961f38ae download
llm.mnn.weight 2.70 GB 0ffdcd81 download
audio.mnn.weight 566 MB 9a74d294 download
visual.mnn.weight 216 MB 77b52589 download
tokenizer.mtok 9.60 MB e08a1293 download
llm.mnn.json 7.20 MB d896c39a download
llm.mnn 3.30 MB c9e6f9d7 download
audio.mnn 1.36 MB 7375d3a9 download
visual.mnn 1.01 MB 6003978c download
.gitattributes 1.82 KB 90fd5794 download
README.md 1.42 KB b14128e1 download
llm_config.json 1.38 KB 3d783dd1 download
export_args.json 1.19 KB 0602e0ce download
config.json 694 B 83f77c45 download

README current version from Hugging Face

license: gemma
license_link: https://ai.google.dev/gemma/docs/gemma_4_license
base_model:

  • huihui-ai/Huihui-gemma-4-E4B-it-abliterated
    tags:
  • mnn
  • mobile
  • tokforge
  • abliterated
  • uncensored
  • gemma-4

TokForge

Runs on-device in the TokForge app.

Huihui-gemma-4-E4B-it-abliterated (TokForge MNN bundle)

MNN-format mobile bundle of huihui-ai/Huihui-gemma-4-E4B-it-abliterated for the TokForge Android app.

Schema

  • TokForge RC20.20.65+ taobao schema (compatible with taobao-mnn/gemma-4-E2B-it-MNN reference)
  • llm.mnn + llm.mnn.weight (q4 / blocksize 64, hqq)
  • ple_embeddings_int4.bin — Per-Layer Embeddings, INT4
  • tokenizer.mtok — TokForge MNN tokenizer
  • visual.mnn + audio.mnn — multimodal encoders
  • llm_config.json — model_type: gemma4, with ple_embed_file + ple_quant

Export

  • Date: 2026-04-25
  • Exporter commit: b3a2952b6
  • Build: MNN-tokforge-working-tq-merged/build-host-llm/MNNConvert

License

Inherits the Gemma Terms of Use from the base model. Upstream model is Apache-2.0 weights under Gemma terms.

README history 4 versions

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

  1. 2026-07-04Add TokForge app links7f328271.4 KB
    Loading...
  2. 2026-04-25Cycle10 taobao-schema re-export 2026-04-2511b1e841.2 KB
    Loading...
  3. 2026-04-12Sync verified TokForge 3.4.9 Gemma 4 MNN bundle208dd302 KB
    Loading...
  4. 2026-04-12Add README.md (Q4+int4 PLE, requires TokForge 3.4.9)2ccd7433.4 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