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

Nekotekina/Llama-4-Maverick-17B-128E-Instruct-Projected-Abliterated-GGUF

Nekotekina Llama 17B GGUF multimodal 1.0M 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%2FLlama-4-Maverick-17B-128E-Instruct-Projected-Abliterated-GGUF"
Response includes
  • classification m8
  • files 16
  • hub_downloads_all_time 3,710
  • author_summary 3 models
  • readme_text full
Try next
GET/models?author=Nekotekina
All 3 models by Nekotekina
 GET/models?family=llama&method=m8
Sibling llama 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
4K
232 last 30d - cooling
Likes
5
Model age
9mo ago
created 2025-12-23
Downloads over time
Now3.8K→from108↑3,442%
01.4K2.8K4.2K108 on Dec 24, 20253.8K on Oct 11Dec '25FebAprJunAugOct
Dec 24, 2025 → Oct 11 · 81 snapshots · spans 291 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.

meta-llama/Llama-4-Maverick-17B-128E this lineage
Nekotekina/Llama-4-Maverick-17B-128E-Instruct-Projected-Abliterated-GGUF↓ 232

Metadata

License
llama4
Quantizations
Q4_K
Tags
gguf meta llama llama-4 conversational image-text-to-text base_model:meta-llama/Llama-4-Maverick-17B-128E base_model:quantized:meta-llama/Llama-4-Maverick-17B-128E license:llama4 endpoints_compatible region:us imatrix

Related

Other by Nekotekina
Llama-4-Scout-17B-16E-Instruct-Projected-Abliterated-GGUF 154 Qwen3-VL-235B-A22B-Instruct-Projected-Abliterated-GGUF 97
Same base model
nguyenthilaitrieulong/Llama-4-Maverick-17B-128E-Instruct-Projected-Abliterated-GGUF 135 qwe2111/Llama-4-Maverick-17B-128E-Instruct-Projected-Abliterated-GGUF 105
Total size
613 GB
Files
16
Quantizations
2
Registered
2026-08-22 13:56
Last updated on HF
2025-12-24 09:30
Source huggingface.co/Nekotekina/Llama-4-Maverick-17B-128E-Instruct-Projected-Abliterated-GGUF ↗ Base model meta-llama/Llama-4-Maverick-17B-128E ↗

Files by quantization

Q4_K 5 files 216 GB
Llama-4-Maverick-17B-128E-PAB-Q4_K_XL-00001-of-00005.gguf 46.5 GB b94bba7b download
Llama-4-Maverick-17B-128E-PAB-Q4_K_XL-00003-of-00005.gguf 46.4 GB a03ed5a1 download
Llama-4-Maverick-17B-128E-PAB-Q4_K_XL-00002-of-00005.gguf 46.4 GB e403ac8f download
Llama-4-Maverick-17B-128E-PAB-Q4_K_XL-00004-of-00005.gguf 46.1 GB 5a0138a1 download
Llama-4-Maverick-17B-128E-PAB-Q4_K_XL-00005-of-00005.gguf 30.9 GB 6a76332e download
Auxiliary files 11 files 397 GB
Llama-4-Maverick-17B-128E-PAB-Q8_0-00008-of-00009.gguf 46.5 GB 2f1a7664 download
Llama-4-Maverick-17B-128E-PAB-Q8_0-00009-of-00009.gguf 46.5 GB 9861b8bb download
Llama-4-Maverick-17B-128E-PAB-Q8_0-00001-of-00009.gguf 45.0 GB 82fa509c download
Llama-4-Maverick-17B-128E-PAB-Q8_0-00006-of-00009.gguf 45.0 GB 3ccddf62 download
Llama-4-Maverick-17B-128E-PAB-Q8_0-00003-of-00009.gguf 43.5 GB 1871ea74 download
Llama-4-Maverick-17B-128E-PAB-Q8_0-00002-of-00009.gguf 42.5 GB 817cb6c9 download
Llama-4-Maverick-17B-128E-PAB-Q8_0-00004-of-00009.gguf 42.5 GB f63b988d download
Llama-4-Maverick-17B-128E-PAB-Q8_0-00005-of-00009.gguf 42.5 GB 06431e6e download
Llama-4-Maverick-17B-128E-PAB-Q8_0-00007-of-00009.gguf 42.5 GB 4e65433b download
.gitattributes 2.83 KB 7bc8971c download
README.md 846 B 47fb2bdb download

README current version from Hugging Face

license: llama4
base_model:

  • meta-llama/Llama-4-Maverick-17B-128E
    pipeline_tag: image-text-to-text
    tags:
  • meta
  • llama
  • llama-4
  • conversational

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/Llama-4-Maverick-17B-128E-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. 2025-12-23Update README.mdc4923a9846 B
    Loading...
  2. 2025-12-23initial commit93a626324 B
    Loading...

Discussions 1 thread

  1. 2026-08-02Model well done!open1 💬#1
    Loading...

Continue on Hugging Face →

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