kaitchup/MiniMax-M3-GGUF-MoQ overview
<div align="center" <img src="https://cdn uploads.huggingface.co/production/uploads/64b93e6bd6c468ac7536607e/mj6xac74jHGLqymiovObc.png" alt="The Kaitchup AI on…
Runs locally from ~123.18 GB disk (32 GB+ VRAM class GPUs with llama.cpp / guIDE).
Repository Files & Downloads
| File | Type | Quantization | Size | Link |
|---|---|---|---|---|
| MoQ-2.5.gguf | GGUF | GGUF | 123.18 GB | Download |
| MoQ-2.75.gguf | GGUF | GGUF | 135.20 GB | Download |
| MoQ-3.0.gguf | GGUF | GGUF | 148.57 GB | Download |
| MoQ-3.25.gguf | GGUF | GGUF | 153.24 GB | Download |
| MoQ-3.5.gguf | GGUF | GGUF | 171.27 GB | Download |
| MoQ-3.75.gguf | GGUF | GGUF | 185.59 GB | Download |
| MoQ-4.75.gguf | GGUF | GGUF | 189.31 GB | Download |
| MoQ-5.0.gguf | GGUF | GGUF | 239.41 GB | Download |
Model Details
Model README
---
license: other
license_name: minimax-community
license_link: LICENSE
base_model:
- MiniMaxAI/MiniMax-M3
---
<div align="center">
<img
src="https://cdn-uploads.huggingface.co/production/uploads/64b93e6bd6c468ac7536607e/mj6xac74jHGLqymiovObc.png"
alt="The Kaitchup -- AI on a Budget"
style="width: 100%; max-width: 100%; height: auto; display: inline-block; margin-bottom: 0.5em; margin-top: 0.5em;"
/>
<div style="display: flex; justify-content: center; gap: 0.5em; margin-bottom: 1em;">
<a href="https://kaitchup.substack.com/subscribe"><strong>Subscribe and Support</strong></a>
</div>
</div>
GGUF models made with the method ("Mixture of Quantizations") proposed by Waleed Ahmad.
I also used Unsloth M3's imatrix for calibration.
More details and evaluation here:
MiniMax M3 GGUF Quantization: From 852 GB to ~150 GB Without Breaking Accuracy
Avoid using the MoQ-2.5.
- Compute Sponsorship: Verda. I used 2 B300s for quantization and evaluation.
Run kaitchup/MiniMax-M3-GGUF-MoQ with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.
Source: Hugging Face · Compare models