Instructions to use unsloth/MiniMax-M3.1-Flash-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 unsloth/MiniMax-M3.1-Flash-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 unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
llama cli -hf unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./llama-cli -hf unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL

Use Docker

docker model run hf.co/unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL

LM Studio
Jan

vLLM

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

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "unsloth/MiniMax-M3.1-Flash-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": "unsloth/MiniMax-M3.1-Flash-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/unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL

Ollama
How to use unsloth/MiniMax-M3.1-Flash-GGUF with Ollama:
```
ollama run hf.co/unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL
```
Unsloth Desktop

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL

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": "unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Docker Model Runner
How to use unsloth/MiniMax-M3.1-Flash-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL

Run and chat with the model

lemonade run user.MiniMax-M3.1-Flash-GGUF-UD-Q4_K_XL

List all available models

lemonade list

Hermes Agent

How to use unsloth/MiniMax-M3.1-Flash-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 unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL

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 unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL

Run Hermes

hermes

Atomic Chat

OpenClaw

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

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama serve -hf unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL

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 "unsloth/MiniMax-M3.1-Flash-GGUF:UD-Q4_K_XL" \
  --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"

Work in progress

MiniMax-M3.1-Flash is a native multimodal mixture-of-experts model for coding, agentic workflows, computer use, and cybersecurity. It supports text, image, and video inputs with a context window of up to 1M tokens.

Building on MiniMax-M3, M3.1-Flash improves task performance and inference efficiency with sparse attention throughout the model, quantization-aware training, and DSpark speculative decoding.

Highlights:

Agentic performance: A generational leap in agentic tasks, coding, and cybersecurity — 76.2 on BankerToolBench, 73.7% on DeepSWE v1.1, 61.7 on OSWorld V2, 29.6 on Agents' Last Exam, and 82.2 on CyberGym.
Efficient by design: Sparse attention throughout, quantization-aware training, and DSpark speculative decoding improve inference efficiency.

Model at a Glance

Architecture: Native multimodal mixture-of-experts (MoE)
Parameters: Approximately 428B total; 23B activated per token
Inputs / output: Text, image, and video inputs; text output
Context window: Up to 1,000,000 tokens
Attention: MiniMax Sparse Attention (MSA) throughout the model
Speculative decoding: DSpark draft head included

Benchmarks

Benchmark	MiniMax M3.1 Flash	DeepSeek V4.1 Flash-1017	DeepSeek V4.1 Flash	Kimi K3	GLM-5.3	GPT-5.6 Sol	Opus 5
Automation-Bench v1.0.6	62.8	60.5	54.8	46.7	48.8	45.8	50.3
BankerToolBench	76.2	—	73.7	69.1	74.5	74.6	76.2
GDP.pdf AA	20.8	—	12.8	22.0	11.2	27.2	21.6
Terminal Bench 4.0	38.1	42.3	31.2	12.6	37.9	39.9	51.8
LOCA-Bench 256K	60.3	—	—	49.7	50.3	60.0	53.7
Agents’ Last Exam	29.6	—	—	28.3	—	30.6	32.2
OSWorld 2.0	61.7	—	54.3	58.3	—	65.7	70.6
PostTrain Bench v1.1	39.3	—	30.5	36.6	37.5	36.2	40.4
DeepSWE v1.1	73.7	77.0	74.2	67.5	66.9	73.0	74.0
NL2Repo-Bench	61.2	68.2	65.4	58.0	58.0	56.8	75.3
SWE Refactor Bench	23.0	—	11.8	19.5	10.4	28.5	31.0
CyberGym	82.2	—	—	80.0	84.5	83.6	—
BabyVision (with tools)	91.0	92.5	89.6	85.7	—	88.9	94.1
HLE (without tools)	43.4	42.6	39.2	43.5	42.3	49.5	55.6
CharXiv RQ	82.5	—	69.0	84.8	—	85.2	83.7

Evaluation Notes

Automation-Bench v1.0.6: 600 publicly released tasks.
BankerToolBench: OpenCode 1.17.18; MiniMax-M2.7 judge.
GDP.pdf AA: Taken directly from Artificial Analysis.
Terminal Bench 4.0: Codex 0.149.1.
LOCA-Bench 256K: Official implementation.
Agents’ Last Exam: Official Overall setting; full-set results from the official ALE leaderboard only. Blank = no official result (CLI-only excluded), not zero.
OSWorld 2.0: 0808 Full release; highest reported per model at release, except DeepSeek V4.1 (in-house reproduction).
PostTrain Bench v1.1: Claude Code 2.1.251, 512K context; otherwise official setup.
DeepSWE v1.1: mini-SWE-agent 2.4.5, 512K context.
NL2Repo-Bench: Claude Code 2.1.233, 512K context; reward hacking = 0; two inconsistent tasks corrected (scores use the corrected set).
SWE Refactor Bench: Claude Code 2.1.220, 200K context; otherwise official setup.
CyberGym: Claude Code 2.1.263, 1M context.
BabyVision (with tools): Claude Code 2.1.285; min image side 1,500 px.
HLE (without tools): Text-only subset (2,158 questions).
CharXiv RQ: GPT-5.5 judge.

Results are for the official weights; third-party quantizations may differ.

What’s New in M3.1-Flash

M3.1-Flash retains M3’s core mixture-of-experts architecture, with three main changes:

Sparse attention throughout: the first three full-attention layers are replaced with sparse attention.
Quantization-aware training: the routed MoE experts and the attention paths are quantized during training, reducing memory footprint and improving serving efficiency.
DSpark speculative decoding: DSpark replaces the earlier EAGLE-like MTP approach. The release includes the draft head for use with compatible serving implementations.

How to Use

Multi-Chip Deployment

FlagOS — see Multi-Chip Support and Downloads.

Inference Settings

Recommended sampling settings: temperature=1.0 and top_p=0.95.

For reasoning, set reasoning_effort in the chat template: low, medium, high, xhigh, or max.

The model supports a context window of up to 1M tokens. Usable context length and throughput depend on GPU memory and the serving configuration.

Contact Us

Downloads last month: -

GGUF

Model size

426B params

Architecture

minimax-m3

Hardware compatibility

4-bit

8-bit

Model tree for unsloth/MiniMax-M3.1-Flash-GGUF

Base model

MiniMaxAI/MiniMax-M3.1-Flash

Quantized

(22)

this model

Paper for unsloth/MiniMax-M3.1-Flash-GGUF

MiniMax Sparse Attention

Paper • 2606.13392 • Published Jun 11 • 171