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

Phil2Sat/Goetia-26B-A4B-v1.4-LazyLora-heresy-I-Compact-MXFP4.gguf overview

Just my Frankenquant to fit into 16GB with fixed imatrix.

ggufbase_model:MuXodious/Goetia-26B-A4B-v1.4-LazyLora-heresybase_model:quantized:MuXodious/Goetia-26B-A4B-v1.4-LazyLora-heresyendpoints_compatibleregion:usimatrixconversational

Runs locally from ~54.3 MB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
Author

Repository Files & Downloads

3 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Goetia-26B-A4B-v1.4-LazyLora-heresy-I-Compact-MXFP4.ggufGGUFGGUF12.05 GBDownload
Goetia-imatrix-own.ggufGGUFGGUF54.3 MBDownload
mmproj-Goetia-26B-A4B-v1.4-LazyLora-heresy-BF16.ggufGGUFBF161.11 GBDownload

Model Details

Model IDPhil2Sat/Goetia-26B-A4B-v1.4-LazyLora-heresy-I-Compact-MXFP4.gguf
AuthorPhil2Sat
Pipeline
License
Base modelMuXodious/Goetia-26B-A4B-v1.4-LazyLora-heresy
Last modified2026-08-04T18:35:53.000Z

Model README

---

base_model:

  • MuXodious/Goetia-26B-A4B-v1.4-LazyLora-heresy

---

Just my Frankenquant to fit into 16GB with fixed imatrix.

Run Phil2Sat/Goetia-26B-A4B-v1.4-LazyLora-heresy-I-Compact-MXFP4.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