GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →
Model Intelligence Sheet

qwe2111/Llama-4-Maverick-17B-128E-Instruct-Projected-Abliterated-GGUF overview

Experimental abliterated model using improved https://huggingface.co/blog/grimjim/projected abliteration technique. Abliteration tries to remove refusals from …

ggufmetallamallama-4conversationalimage-text-to-textbase_model:meta-llama/Llama-4-Maverick-17B-128Ebase_model:quantized:meta-llama/Llama-4-Maverick-17B-128Elicense:llama4endpoints_compatibleregion:usimatrix

Runs locally from ~30.88 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
image-text-to-text
Author

Repository Files & Downloads

14 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Llama-4-Maverick-17B-128E-PAB-Q4_K_XL-00001-of-00005.ggufGGUFQ4_K_XL46.45 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q4_K_XL-00002-of-00005.ggufGGUFQ4_K_XL46.41 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q4_K_XL-00003-of-00005.ggufGGUFQ4_K_XL46.41 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q4_K_XL-00004-of-00005.ggufGGUFQ4_K_XL46.11 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q4_K_XL-00005-of-00005.ggufGGUFQ4_K_XL30.88 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q8_0-00001-of-00009.ggufGGUFQ8_044.99 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q8_0-00002-of-00009.ggufGGUFQ8_042.50 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q8_0-00003-of-00009.ggufGGUFQ8_043.52 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q8_0-00004-of-00009.ggufGGUFQ8_042.50 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q8_0-00005-of-00009.ggufGGUFQ8_042.50 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q8_0-00006-of-00009.ggufGGUFQ8_044.97 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q8_0-00007-of-00009.ggufGGUFQ8_042.50 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q8_0-00008-of-00009.ggufGGUFQ8_046.55 GBDownload
Llama-4-Maverick-17B-128E-PAB-Q8_0-00009-of-00009.ggufGGUFQ8_046.55 GBDownload

Model Details

Model IDqwe2111/Llama-4-Maverick-17B-128E-Instruct-Projected-Abliterated-GGUF
Authorqwe2111
Pipelineimage-text-to-text
Licensellama4
Base modelmeta-llama/Llama-4-Maverick-17B-128E
Last modified2026-07-04T17:32:34.000Z

Model README

---

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.

Run qwe2111/Llama-4-Maverick-17B-128E-Instruct-Projected-Abliterated-GGUF with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models

Source: Hugging Face · Compare models