What license applies to avar6/minimax-m3-MSA-gguf?

License: See model card. Verify terms on Hugging Face before commercial use.

How do I run avar6/minimax-m3-MSA-gguf locally?

Download a GGUF file from this page and load it in guIDE or llama.cpp. Pipeline task: text-generation.

Model Intelligence Sheet

avar6/minimax-m3-MSA-gguf overview

Q: What is avar6/minimax-m3-MSA-gguf?

--- base_model: - MiniMaxAI/MiniMax-M3 tags: - gguf - msa - minimax-m3 --- These are standard llamacpp ggufs with MSA intact. They are experimental and made with a work in progress fork of llamacpp https://github.com/timkhronos/llama.cpp/tree/MSA. MSA and vision are currently functioning. The vision mmproj can be found here https://huggingface.co/Serpen/Minimax_M3_MMPROJ_GGUF You can learn more about these ggufs and the fork on the beaver ai discord. We do plan to submit a pull request https://discord.gg/beaverai

These are standard llamacpp ggufs with MSA intact. They are experimental and made with a work in progress fork of llamacpp https://github.com/timkhronos/llama.…

ggufmsaminimax-m3base_model:MiniMaxAI/MiniMax-M3base_model:quantized:MiniMaxAI/MiniMax-M3endpoints_compatibleregion:usconversational

Runs locally from ~7.53 GB disk (8 GB VRAM class GPUs with llama.cpp / guIDE).

Downloads

Likes

Pipeline

—

Author

avar6

Repository Files & Downloads

21 GGUF files detected

Direct downloads for local inference

File	Type	Quantization	Size	Link
IQ6_k/minimax-m3-MSA-Q6_K.gguf-00001-of-00008.gguf	GGUF	IQ6_K	46.13 GB	Download
IQ6_k/minimax-m3-MSA-Q6_K.gguf-00002-of-00008.gguf	GGUF	IQ6_K	45.34 GB	Download
IQ6_k/minimax-m3-MSA-Q6_K.gguf-00003-of-00008.gguf	GGUF	IQ6_K	45.34 GB	Download
IQ6_k/minimax-m3-MSA-Q6_K.gguf-00004-of-00008.gguf	GGUF	IQ6_K	45.34 GB	Download
IQ6_k/minimax-m3-MSA-Q6_K.gguf-00005-of-00008.gguf	GGUF	IQ6_K	45.34 GB	Download
IQ6_k/minimax-m3-MSA-Q6_K.gguf-00006-of-00008.gguf	GGUF	IQ6_K	45.34 GB	Download
IQ6_k/minimax-m3-MSA-Q6_K.gguf-00007-of-00008.gguf	GGUF	IQ6_K	45.34 GB	Download
IQ6_k/minimax-m3-MSA-Q6_K.gguf-00008-of-00008.gguf	GGUF	IQ6_K	7.53 GB	Download
Q4_K_M/minimax-m3-MSA-Q4_KM.gguf-00001-of-00006.gguf	GGUF	Q4_K_M	45.89 GB	Download
Q4_K_M/minimax-m3-MSA-Q4_KM.gguf-00002-of-00006.gguf	GGUF	Q4_K_M	46.38 GB	Download
Q4_K_M/minimax-m3-MSA-Q4_KM.gguf-00003-of-00006.gguf	GGUF	Q4_K_M	45.85 GB	Download
Q4_K_M/minimax-m3-MSA-Q4_KM.gguf-00004-of-00006.gguf	GGUF	Q4_K_M	46.38 GB	Download
Q4_K_M/minimax-m3-MSA-Q4_KM.gguf-00005-of-00006.gguf	GGUF	Q4_K_M	46.17 GB	Download
Q4_K_M/minimax-m3-MSA-Q4_KM.gguf-00006-of-00006.gguf	GGUF	Q4_K_M	8.89 GB	Download
Q5_K/minimax-m3-MSA-Q5_K.gguf-00001-of-00007.gguf	GGUF	Q5_K	45.11 GB	Download
Q5_K/minimax-m3-MSA-Q5_K.gguf-00002-of-00007.gguf	GGUF	Q5_K	45.29 GB	Download
Q5_K/minimax-m3-MSA-Q5_K.gguf-00003-of-00007.gguf	GGUF	Q5_K	45.52 GB	Download
Q5_K/minimax-m3-MSA-Q5_K.gguf-00004-of-00007.gguf	GGUF	Q5_K	45.22 GB	Download
Q5_K/minimax-m3-MSA-Q5_K.gguf-00005-of-00007.gguf	GGUF	Q5_K	45.29 GB	Download
Q5_K/minimax-m3-MSA-Q5_K.gguf-00006-of-00007.gguf	GGUF	Q5_K	44.87 GB	Download
Q5_K/minimax-m3-MSA-Q5_K.gguf-00007-of-00007.gguf	GGUF	Q5_K	10.04 GB	Download

Model Details

Model ID	avar6/minimax-m3-MSA-gguf
Author	avar6
Pipeline	—
License	—
Base model	MiniMaxAI/MiniMax-M3
Last modified	2026-06-20T18:12:37.000Z

Model README

---

base_model:

MiniMaxAI/MiniMax-M3

tags:

gguf
msa
minimax-m3

---

These are standard llamacpp ggufs with MSA intact. They are experimental and made with a work in progress fork of llamacpp https://github.com/timkhronos/llama.cpp/tree/MSA. MSA and vision are currently functioning. The vision mmproj can be found here https://huggingface.co/Serpen/Minimax_M3_MMPROJ_GGUF

You can learn more about these ggufs and the fork on the beaver ai discord. We do plan to submit a pull request https://discord.gg/beaverai

Run avar6/minimax-m3-MSA-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