Instructions to use peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Notebooks
Google Colab
Kaggle
Local Apps Settings

How to use peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS
# Run inference directly in the terminal:
llama cli -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS
# Run inference directly in the terminal:
llama cli -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS

Build from source code

git clone https://github.com/ggml-org/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-app
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama serve -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS
# Run inference directly in the terminal:
./build/bin/llama cli -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS

Use Docker

docker model run hf.co/peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS

Llama new
LM Studio
Jan

vLLM

How to use peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS

Ollama
How to use peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF with Ollama:
```
ollama run hf.co/peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS
```
Unsloth Desktop

How to use peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF with Docker Model Runner:
```
docker model run hf.co/peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS
```

Lemonade

How to use peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS

Run and chat with the model

lemonade run user.MiniMax-M3.1-Flash-Maya-GGUF-IQ2_XXS

List all available models

lemonade list

Hermes Agent

How to use peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS

Configure Hermes

# Install Hermes:
curl -fsSL https://hermes-agent.nousresearch.com/install.sh | bash
hermes setup
# Point Hermes at the local server:
hermes config set model.provider custom
hermes config set model.base_url http://127.0.0.1:8080/v1
hermes config set model.default peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF with OpenClaw:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS

Configure OpenClaw

# Install OpenClaw:
npm install -g openclaw@latest
# Register the local server and set it as the default model:
openclaw onboard --non-interactive --mode local \
  --auth-choice custom-api-key \
  --custom-base-url http://127.0.0.1:8080/v1 \
  --custom-model-id "peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF:IQ2_XXS" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

openclaw agent --local --agent main --message "Hello from Hugging Face"

MiniMax-M3.1-Flash · Maya GGUF

GGUF quantizations of MiniMaxAI/MiniMax-M3.1-Flash (428B parameters, 23B active per token: 128 routed experts per layer, 4 active, plus a shared expert; sparse attention in every layer; up to a 1M-token context), made for Project Maya. Project Maya keeps the most-used experts on the GPU and computes the rest from RAM, so the model runs well below its size. Both quants are made from MiniMax's own release (FP4 experts, FP8 dense weights), not from a re-quantized file, and keep every expert.

Two quants

	Maya-S	Maya-XS
Made for	the closest answers to the original	the whole model in a 128 GB PC's memory
Model in memory	122.4 GB	93.0 GB
Routed experts	IQ2_XXS; the most sensitive layers' tensors IQ2_XS / IQ2_S / IQ3_XXS	IQ1_S; the most sensitive layers' tensors IQ2_XXS
Attention and sparse-attention indexer	Q8_0	Q5_K / Q6_K; indexer Q8_0
Shared experts, dense layers, embeddings, output	Q6_K	Q5_K / Q4_K / Q6_K
Next-token loss (NLL) vs the original	+0.8%	+5.0%

Quality: the same top token as the original

Category	Maya-S	Maya-XS
Tool calls and agents	92.1%	88.8%
three.js / WebGL / canvas	92.0%	88.5%
Web front-end	94.6%	91.7%
Code	93.7%	90.9%
Reasoning	85.9%	80.4%
Chat	76.4%	66.5%
Multilingual chat	78.5%	71.6%
Average of the categories	87.6%	82.6%

Measured on held-out conversations never used for calibration, on the model's own answers, against the original model's predictions (MiniMax's released weights, decoded exactly), with the files as published running in Project Maya's engine - the same results on NVIDIA and AMD.

How they were made

Calibration text in MiniMax's own chat format, thinking included: tool calls and agent traces, code (with three.js / canvas / WebGL and other front-end work), reasoning, long answers, chat, multilingual chat - 384 sequences of 2,048 tokens. A separate held-out set is kept for evaluation.
Statistics from the model itself, layer by layer: an importance matrix for every expert separately.
Where the bits go: every layer's gate, up and down matrices were measured in each candidate type, and the extra bits went to the layers where the model is most sensitive.
Error-feedback rounding of every expert, at the quantizer's 256-weight blocks, each expert against its own input statistics - and each layer calibrated on what the already-quantized layers before it produce.
llama.cpp's own quantizers (ggml), so the files are ordinary GGUFs in llama.cpp's minimax-m3 layout.

Files

Folder	Files	Size
`Maya-S/`	`MiniMax-M3.1-Flash-Maya-S-IQ2_XXS-00001-of-00003.gguf` … `-00003-of-00003.gguf`, and `MiniMax-M3.1-Flash-Maya-S-maya-indexers.gguf`	122.4 GB
`Maya-XS/`	`MiniMax-M3.1-Flash-Maya-XS-IQ1_S-00001-of-00002.gguf`, `-00002-of-00002.gguf`, and `MiniMax-M3.1-Flash-Maya-XS-maya-indexers.gguf`	93.0 GB
`dspark/`	MiniMax's DSpark drafter, as MiniMax released it	2.3 GB
`vision/`	MiniMax's vision tower, as MiniMax released it	1.7 GB

MiniMax-M3.1 runs its sparse-attention indexer in every layer. The indexers of layers 0-2 are in the small *-maya-indexers.gguf beside each quant: Project Maya loads them and runs the model as MiniMax defines it; stock llama.cpp loads the shards alone (it runs those three layers with full attention).

Running it

Project Maya sets everything up and runs it (v1.1.30 or later):

git clone https://github.com/mw00/project-maya.git && cd project-maya
./setup.sh --setup --model minimax-maya-s      # Windows: START-MAYA.bat
./setup.sh --setup --model minimax-maya-xs

It checks the PC (NVIDIA from V100 up, or AMD), downloads the files (every one verified by its sha256, resumed if a download stops), compiles the engine for your GPU(s) and starts it: the dashboard at http://127.0.0.1:8080, or the OpenAI- and Anthropic-compatible API at the same address (streaming, tool calls, pictures, MiniMax's thinking levels).

The shards also load in llama.cpp (minimax-m3).

License

The model is MiniMax's MiniMax-M3.1-Flash under the MiniMax Community License (LICENSE): free for non-commercial use; commercial use has conditions, including showing "Built with MiniMax M3.1-Flash". These quantizations are released under the same license.

Downloads last month: 17,747

GGUF

Model size

426B params

Architecture

minimax-m3

Hardware compatibility

1-bit

2-bit

Model tree for peasantsmith/MiniMax-M3.1-Flash-Maya-GGUF

Base model

MiniMaxAI/MiniMax-M3.1-Flash

Quantized

(35)

this model