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

Auguments/Ministral-3-3B-Reasoning-2512-absolute-heresy-GGUF-BF16 overview

MuXodious/Ministral 3 3B Reasoning 2512 absolute heresy I had some weird issues with mradermarcher's quant. This one works for me. Highest quality conversion B…

ggufquantizedbase_model:MuXodious/Ministral-3-3B-Reasoning-2512-absolute-heresybase_model:quantized:MuXodious/Ministral-3-3B-Reasoning-2512-absolute-heresylicense:apache-2.0endpoints_compatibleregion:usconversational

Runs locally from ~2.63 GB disk (4 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads
0
Likes
0
Pipeline
Author

Repository Files & Downloads

2 GGUF files detected
Direct downloads for local inference
FileTypeQuantizationSizeLink
Ministral-3-3B-Reasoning-2512-absolute-heresy-BF16.ggufGGUFBF166.39 GBDownload
Ministral-3-3B-Reasoning-2512-absolute-heresy-Q6_K.ggufGGUFQ6_K2.63 GBDownload

Model Details

Model IDAuguments/Ministral-3-3B-Reasoning-2512-absolute-heresy-GGUF-BF16
AuthorAuguments
Pipeline
Licenseapache-2.0
Base modelMuXodious/Ministral-3-3B-Reasoning-2512-absolute-heresy
Last modified2026-08-31T03:40:45.000Z

Model README

---

base_model: MuXodious/Ministral-3-3B-Reasoning-2512-absolute-heresy

base_model_relation: quantized

library_name: gguf

tags:

  • gguf
  • quantized

license: apache-2.0

---

MuXodious/Ministral-3-3B-Reasoning-2512-absolute-heresy

I had some weird issues with mradermarcher's quant. This one works for me.

---

Highest quality conversion - BF16.

In this repo:

  • Base model in BF16, and Q6_K converted from BF16

For mmproj, use unsloth's.

Run Auguments/Ministral-3-3B-Reasoning-2512-absolute-heresy-GGUF-BF16 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