Model Intelligence Sheet
llmfan46/MiniMax-M3-uncensored-heretic-aggressive-high-precision-pack-GGUF overview
llmfan46/MiniMax-M3-uncensored-heretic-aggressive-high-precision-pack-GGUF GGUF downloads for local AI inference with guIDE.
Runs locally from ~51.25 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
10 GGUF files detected
Direct downloads for local inference
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| BF16/MiniMax-M3-uncensored-heretic-aggressive-BF16.gguf-00001-of-00005.gguf | GGUF | BF16 | 185.95 GB | Download |
| BF16/MiniMax-M3-uncensored-heretic-aggressive-BF16.gguf-00002-of-00005.gguf | GGUF | BF16 | 184.00 GB | Download |
| BF16/MiniMax-M3-uncensored-heretic-aggressive-BF16.gguf-00003-of-00005.gguf | GGUF | BF16 | 184.00 GB | Download |
| BF16/MiniMax-M3-uncensored-heretic-aggressive-BF16.gguf-00004-of-00005.gguf | GGUF | BF16 | 184.31 GB | Download |
| BF16/MiniMax-M3-uncensored-heretic-aggressive-BF16.gguf-00005-of-00005.gguf | GGUF | BF16 | 55.23 GB | Download |
| Q6_K/MiniMax-M3-uncensored-heretic-aggressive-Q6_K.gguf-00001-of-00002.gguf | GGUF | Q6_K | 185.87 GB | Download |
| Q6_K/MiniMax-M3-uncensored-heretic-aggressive-Q6_K.gguf-00002-of-00002.gguf | GGUF | Q6_K | 139.68 GB | Download |
| Q8_0/MiniMax-M3-uncensored-heretic-aggressive-Q8_0.gguf-00001-of-00003.gguf | GGUF | Q8_0 | 184.44 GB | Download |
| Q8_0/MiniMax-M3-uncensored-heretic-aggressive-Q8_0.gguf-00002-of-00003.gguf | GGUF | Q8_0 | 185.93 GB | Download |
| Q8_0/MiniMax-M3-uncensored-heretic-aggressive-Q8_0.gguf-00003-of-00003.gguf | GGUF | Q8_0 | 51.25 GB | Download |
Model Details
| Model ID | llmfan46/MiniMax-M3-uncensored-heretic-aggressive-high-precision-pack-GGUF |
|---|---|
| Author | llmfan46 |
| Pipeline | image-text-to-text |
| License | other |
| Base model | MiniMaxAI/MiniMax-M3 |
| Last modified | 2026-06-19T21:24:04.000Z |
Run llmfan46/MiniMax-M3-uncensored-heretic-aggressive-high-precision-pack-GGUF with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models