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

ahmed22xa/Qwen3.6-27B-huihui-abliterated-NInfer

ahmed22xa Qwen 27B 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/ahmed22xa%2FQwen3.6-27B-huihui-abliterated-NInfer"
Response includes
  • classification m1
  • files 3
  • hub_downloads_all_time 143
  • author_summary 4 models
  • readme_text full
Try next
GET/models?author=ahmed22xa
All 4 models by ahmed22xa
 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
143
Likes
0
Model age
2mo ago
created 2026-07-31
Downloads over time
Now243→from2↑12,050%
0891782672 on Jul 29243 on Oct 11JulAugSepOct
Jul 29 → Oct 11 · 51 snapshots · spans 74 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-Qwen3.6-27B-abliterated↓ 4,286 this lineage
ahmed22xa/Qwen3.6-27B-huihui-abliterated-NInfer↓ 191

Metadata

License
apache-2.0
Tags
ninfer qwen3.6 abliterated vision rtx3090 base_model:Qwen/Qwen3.6-27B base_model:finetune:Qwen/Qwen3.6-27B license:apache-2.0 region:us

Related

Other by ahmed22xa
Qwen3.6-35B-A3B-huihui-abliterated-NInfer 2K Huihui-Qwen3-VL-4B-Instruct-abliterated-comfy 0 Huihui-Qwen3-VL-4B-Thinking-abliterated-comfy 0
Same base model
shawnw3i/Huihui-Qwen3.6-27B-abliterated-AWQ-MTP 19K mradermacher/Huihui-Qwen3.6-27B-abliterated-GGUF 4K mradermacher/Huihui-Qwen3.6-27B-abliterated-i1-GGUF 4K lhca521/Huihui-Qwen3.6-27B-abliterated-AWQ 908 Abiray/Huihui-Qwen3.6-27B-abliterated-GGUF 780
Total size
0 B
Files
3
Quantizations
1
Registered
2026-08-22 13:56
Last updated on HF
2026-07-31 08:21
Source huggingface.co/ahmed22xa/Qwen3.6-27B-huihui-abliterated-NInfer ↗ Base model huihui-ai/Huihui-Qwen3.6-27B-abliterated →

Files by quantization

Auxiliary files 3 files 16.3 GB
qwen3_6_27b_huihui_abliterated.ninfer 16.3 GB 1022d869 download
README.md 1.63 KB 8fee97cd download
.gitattributes 1.56 KB acfbb5ed download

README current version from Hugging Face

license: apache-2.0
base_model:

  • huihui-ai/Huihui-Qwen3.6-27B-abliterated
  • Qwen/Qwen3.6-27B
    tags:
  • ninfer
  • qwen3.6
  • abliterated
  • vision
  • rtx3090
    library_name: ninfer

Qwen3.6-27B (Huihui abliterated) — NInfer container v1

Pre-converted .ninfer artifact for Don-Chad/ninfer-3090 / NInfer (container v1, compatible with prebuilt v0.3.1). Includes vision tensors; usable without --text-only on RTX 3090 24 GB.

Field Value
Filename qwen3_6_27b_huihui_abliterated.ninfer
Size ~16.29 GiB
SHA-256 1022d8695caa5d04528f7633e4b21bcbefd3b6173cd67babdd4af0ab682c3dc2
Source BF16 huihui-ai/Huihui-Qwen3.6-27B-abliterated
Converter upstream tools/convert/qwen3_6_27b (same role-based mixed quant as official NInfer 27B)

Why this exists

NInfer loads only .ninfer at runtime. This upload skips the large BF16 download + local conversion step.

Quick download

hf download ahmed22xa/Qwen3.6-27B-huihui-abliterated-NInfer `
  qwen3_6_27b_huihui_abliterated.ninfer `
  --local-dir models

Example CLI (vision OK)

.\ninfer.exe models\qwen3_6_27b_huihui_abliterated.ninfer `
  --prompt "Hello" --max-new 64 `
  --kv-dtype int8 --mtp-draft-tokens 3 --lm-head-draft `
  --no-thinking

Attribution

Abliteration / BF16: Huihui. Base model: Qwen. NInfer format / converter: Neroued / Don-Chad NInfer projects. See linked model cards and the engine repository for licenses.

README history 1 version

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

  1. 2026-07-31Add model cardfbf5a781.6 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