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

noctrex/Huihui-Qwen3-VL-2B-Thinking-abliterated-GGUF

noctrex Qwen 2B GGUF multimodal second-order 262K ctx
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/noctrex%2FHuihui-Qwen3-VL-2B-Thinking-abliterated-GGUF"
Response includes
  • classification m8
  • files 21
  • hub_downloads_all_time 6,203
  • author_summary 44 models
  • readme_text full
Try next
GET/models?author=noctrex
All 44 models by noctrex
 GET/models?family=qwen&method=m8
Sibling qwen models · same method
 GET/methods/m8
What "m8" means · taxonomy
10 credits · hourly refresh · ~4 KB payload Get an API key →
Abliteration classifier · v1.0.0
M8
Primary method

Repackaging (quantization)

Applied on top of direct removal inherited from the base model.
Confidence
HIGH
Inherited from base model
M1 Direct removal →
Why this label 3 signals
Producer identity confirmed by naming conventions, tags or the model card. This label is very unlikely to change.
  • author=noctrex (M8 quantization producer)
  • is_gguf=1
  • base_model='huihui-ai/Huihui-Qwen3-VL-2B-Thinking-abliterated' looks abliterated -> assume M1
How we label → About M8 →
Refusal direction extraction

No specific extraction method could be identified for this model. The producer either did not document it or used a proprietary pipeline.

What is a refusal direction? →
Downloads · lifetime
6K
557 last 30d - cooling
Likes
1
Model age
11mo ago
created 2025-11-02
Downloads over time
Now6.3K→from315↑1,902%
152.3K4.6K6.9K315 on Nov 5, 20256.3K on Oct 11Nov '25JanMarMayJulSep
Nov 5, 2025 → Oct 11 · 88 snapshots · spans 340 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-VL-2B-Thinking-abliterated↓ 47 this lineage
noctrex/Huihui-Qwen3-VL-2B-Thinking-abliterated-GGUF↓ 557

Metadata

Quantizations
BF16 F16 F32 IQ3 IQ4 Q4_K Q5_K Q6_K Q8_0
Tags
gguf image-text-to-text base_model:huihui-ai/Huihui-Qwen3-VL-2B-Thinking-abliterated base_model:quantized:huihui-ai/Huihui-Qwen3-VL-2B-Thinking-abliterated endpoints_compatible region:us conversational

Related

Other by noctrex
Huihui-Qwen3-VL-4B-Instruct-abliterated-GGUF 28K Huihui-Qwen3-VL-30B-A3B-Instruct-abliterated-GGUF 15K Huihui-Qwen3-VL-8B-Instruct-abliterated-GGUF 9K gemma-4-26B-A4B-it-uncensored-heretic-MXFP4_MOE-GGUF 3K Huihui-Qwen3-VL-2B-Instruct-abliterated-GGUF 3K
Same base model
mradermacher/Huihui-Qwen3-VL-2B-Thinking-abliterated-i1-GGUF 862 mradermacher/Huihui-Qwen3-VL-2B-Thinking-abliterated-GGUF 476
Total size
25.2 GB
Files
21
Quantizations
10
Registered
2026-08-22 13:56
Last updated on HF
2025-11-08 23:33
Source huggingface.co/noctrex/Huihui-Qwen3-VL-2B-Thinking-abliterated-GGUF ↗ Base model huihui-ai/Huihui-Qwen3-VL-2B-Thinking-abliterated →

Files by quantization

F32 2 files 7.93 GB
Huihui-Qwen3-VL-2B-Thinking-abliterated-F32.gguf 6.42 GB 73832124 download
mmproj-F32.gguf 1.52 GB 41e485e2 download
BF16 2 files 3.98 GB
Huihui-Qwen3-VL-2B-Thinking-abliterated-BF16.gguf 3.21 GB 2341c38e download
mmproj-BF16.gguf 784 MB 44b82014 download
F16 2 files 3.97 GB
Huihui-Qwen3-VL-2B-Thinking-abliterated-F16.gguf 3.21 GB cd19ea38 download
mmproj-F16.gguf 781 MB 3a1955e0 download
Q8_0 1 file 1.71 GB
Huihui-Qwen3-VL-2B-Thinking-abliterated-Q8_0.gguf 1.71 GB 11993420 download
Q6_K 1 file 1.32 GB
Huihui-Qwen3-VL-2B-Thinking-abliterated-Q6_K.gguf 1.32 GB 696a9b90 download
Q5_K 2 files 2.32 GB
Huihui-Qwen3-VL-2B-Thinking-abliterated-Q5_K_M.gguf 1.17 GB 2844a8ce download
Huihui-Qwen3-VL-2B-Thinking-abliterated-Q5_K_S.gguf 1.15 GB 5218464b download
Q4_K 2 files 2.02 GB
Huihui-Qwen3-VL-2B-Thinking-abliterated-Q4_K_M.gguf 1.03 GB 0346d17a download
Huihui-Qwen3-VL-2B-Thinking-abliterated-Q4_K_S.gguf 1011 MB 19755cad download
IQ4 2 files 1.92 GB
Huihui-Qwen3-VL-2B-Thinking-abliterated-IQ4_NL.gguf 1006 MB 2666e904 download
Huihui-Qwen3-VL-2B-Thinking-abliterated-IQ4_XS.gguf 964 MB b250eb9e download
IQ3 4 files 3.12 GB
Huihui-Qwen3-VL-2B-Thinking-abliterated-IQ3_M.gguf 854 MB 714f3422 download
Huihui-Qwen3-VL-2B-Thinking-abliterated-IQ3_S.gguf 827 MB 3b708958 download
Huihui-Qwen3-VL-2B-Thinking-abliterated-IQ3_XS.gguf 796 MB 9b86c673 download
Huihui-Qwen3-VL-2B-Thinking-abliterated-IQ3_XXS.gguf 719 MB f0068678 download
Auxiliary files 3 files 2.00 MB
imatrix.gguf 2.00 MB d0064639 download
.gitattributes 3.22 KB 69672de0 download
README.md 830 B 8f428add download

README current version from Hugging Face

pipeline_tag: image-text-to-text
base_model:

  • huihui-ai/Huihui-Qwen3-VL-2B-Thinking-abliterated

These are quantizations of the model Huihui-Qwen3-VL-2B-Thinking-abliterated.

These quantizations were created using an imatrix merged from combined_all_large and harmful.txt to leverage the abliterated nature of the model.

Usage Notes:

  • Download the latest llama.cpp to use these quantizations.
  • Try to use the best quality you can run.
  • For the mmproj file, the F32 version is recommended for best results (F32 > BF16 > F16).

README history 4 versions

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

  1. 2025-11-08Add files using upload-large-folder tool4005d3b830 B
    Loading...
  2. 2025-11-08Add files using upload-large-folder tool99bfca3778 B
    Loading...
  3. 2025-11-08Add files using upload-large-folder tool8fbf92b515 B
    Loading...
  4. 2025-11-02Add files using upload-large-folder tool4e6817e316 B
    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