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

Nekotekina/Qwen3-VL-235B-A22B-Instruct-Projected-Abliterated-GGUF

Nekotekina Qwen 235B GGUF MoE multimodal 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/Nekotekina%2FQwen3-VL-235B-A22B-Instruct-Projected-Abliterated-GGUF"
Response includes
  • classification m8
  • files 14
  • benchmarks 11 entries
  • hub_downloads_all_time 1,356
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=Nekotekina
All 3 models by Nekotekina
 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
MEDIUM
Inherited from base model
M1 Direct removal →
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=1
  • assume M1 (base ablation) + M8 (GGUF quant) - default when producer unknown
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
1K
97 last 30d - cooling
Likes
2
Model age
9mo ago
created 2025-12-20
Downloads over time
Now1.4K→from59↑2,276%
05121K1.5K59 on Dec 24, 20251.4K on Oct 11Dec '25FebAprJunAugOct
Dec 24, 2025 → Oct 11 · 81 snapshots · spans 291 days

Benchmarks

Portrait before abliteration
Benchmarks of the base model as it stood before the refusal-removal operation. Compare with the numbers above to see what the operation cost.
Benchmark Score Source
Entertainment 2.2 UGI
Hazardous 5.9 UGI
Natural Intelligence 28.43 UGI
Political lean -22.7% UGI
Sensitive-Info 39.59 UGI
SocPol 4.6 UGI
UGI 45.56 UGI
Willingness (10) 5.8 UGI
W10-Adherence 6.5 UGI
W10-Direct 5 UGI
Writing 43 UGI

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.

Qwen/Qwen3-VL-235B-A22B-Instruct this lineage
Nekotekina/Qwen3-VL-235B-A22B-Instruct-Projected-Abliterated-GGUF↓ 97

Metadata

License
apache-2.0
Quantizations
Q6_K
Tags
gguf GGUF conversational qwen qwen3 qwen3vl_moe image-text-to-text base_model:Qwen/Qwen3-VL-235B-A22B-Instruct base_model:quantized:Qwen/Qwen3-VL-235B-A22B-Instruct license:apache-2.0 endpoints_compatible region:us

Related

Other by Nekotekina
Llama-4-Maverick-17B-128E-Instruct-Projected-Abliterated-GGUF 232 Llama-4-Scout-17B-16E-Instruct-Projected-Abliterated-GGUF 154
Same base model
huihui-ai/Huihui-Qwen3-VL-235B-A22B-Instruct-abliterated-GGUF 2K FiditeNemini/Qwen3-VL-235B-A22B-Instruct-Abliterated-3bit 98
Total size
419 GB
Files
14
Quantizations
3
Registered
2026-08-22 13:56
Last updated on HF
2025-12-21 10:32
Source huggingface.co/Nekotekina/Qwen3-VL-235B-A22B-Instruct-Projected-Abliterated-GGUF ↗ Base model Qwen/Qwen3-VL-235B-A22B-Instruct ↗

Files by quantization

Q6_K 5 files 187 GB
Qwen3-VL-235B-A22B-PAB-Q6_K_XL-00003-of-00005.gguf 46.5 GB 7f8e7dc0 download
Qwen3-VL-235B-A22B-PAB-Q6_K_XL-00001-of-00005.gguf 46.2 GB b51ddade download
Qwen3-VL-235B-A22B-PAB-Q6_K_XL-00004-of-00005.gguf 46.2 GB e5ed5b1f download
Qwen3-VL-235B-A22B-PAB-Q6_K_XL-00002-of-00005.gguf 46.1 GB 4b38c512 download
Qwen3-VL-235B-A22B-PAB-Q6_K_XL-00005-of-00005.gguf 1.60 GB 1c3044fa download
BF16 1 file 1.08 GB
mmproj-BF16.gguf 1.08 GB 03bc40b1 download
Auxiliary files 8 files 233 GB
Qwen3-VL-235B-A22B-PAB-Q8_0-00005-of-00006.gguf 46.6 GB 3d0e6ac1 download
Qwen3-VL-235B-A22B-PAB-Q8_0-00004-of-00006.gguf 46.0 GB e17c8e1a download
Qwen3-VL-235B-A22B-PAB-Q8_0-00003-of-00006.gguf 45.9 GB fd6cafa2 download
Qwen3-VL-235B-A22B-PAB-Q8_0-00002-of-00006.gguf 45.9 GB 5eadfa90 download
Qwen3-VL-235B-A22B-PAB-Q8_0-00001-of-00006.gguf 45.9 GB 026dd36b download
Qwen3-VL-235B-A22B-PAB-Q8_0-00006-of-00006.gguf 2.53 GB a1560e64 download
.gitattributes 2.45 KB adce34a2 download
README.md 850 B 40799141 download

README current version from Hugging Face

license: apache-2.0
base_model:

  • Qwen/Qwen3-VL-235B-A22B-Instruct
    pipeline_tag: image-text-to-text
    tags:
  • GGUF
  • conversational
  • qwen
  • qwen3
  • qwen3vl_moe

Experimental abliterated model using improved https://huggingface.co/blog/grimjim/projected-abliteration technique. Abliteration tries to remove refusals from model's behaviour without fine-tuning.

For non-abliterated GGUF quantized version I recommend https://huggingface.co/unsloth/Qwen3-VL-235B-A22B-Instruct-GGUF quants.

Warning: Safety guardrails and refusal mechanisms have been broken through abliteration. This model may generate harmful content and shall not be used in production, user-facing applications, etc. You will be solely responsible for its outputs.

Warning 2: Neither removal of refusals nor preservation of original model's capabilies is guaranteed.

README history 2 versions

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

  1. 2025-12-21Fix README.mda2a9120850 B
    Loading...
  2. 2025-12-21Create README.mdded1209166 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