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

Libraries

How to use unsloth/MiniMax-M3-GGUF with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="unsloth/MiniMax-M3-GGUF")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("unsloth/MiniMax-M3-GGUF", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use unsloth/MiniMax-M3-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-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf unsloth/MiniMax-M3-GGUF:UD-Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf unsloth/MiniMax-M3-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
llama cli -hf unsloth/MiniMax-M3-GGUF:UD-Q4_K_M

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-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf unsloth/MiniMax-M3-GGUF:UD-Q4_K_M

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-GGUF:UD-Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf unsloth/MiniMax-M3-GGUF:UD-Q4_K_M

Use Docker

docker model run hf.co/unsloth/MiniMax-M3-GGUF:UD-Q4_K_M

LM Studio
Jan

vLLM

How to use unsloth/MiniMax-M3-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-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-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-GGUF:UD-Q4_K_M

SGLang

How to use unsloth/MiniMax-M3-GGUF with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "unsloth/MiniMax-M3-GGUF" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/MiniMax-M3-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 images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "unsloth/MiniMax-M3-GGUF" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "unsloth/MiniMax-M3-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"
						}
					}
				]
			}
		]
	}'

Ollama
How to use unsloth/MiniMax-M3-GGUF with Ollama:
```
ollama run hf.co/unsloth/MiniMax-M3-GGUF:UD-Q4_K_M
```

Unsloth Studio

How to use unsloth/MiniMax-M3-GGUF with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/MiniMax-M3-GGUF to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for unsloth/MiniMax-M3-GGUF to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for unsloth/MiniMax-M3-GGUF to start chatting

How to use unsloth/MiniMax-M3-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-GGUF:UD-Q4_K_M

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/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-GGUF:UD-Q4_K_M"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

OpenClaw new

How to use unsloth/MiniMax-M3-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-GGUF:UD-Q4_K_M

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-GGUF:UD-Q4_K_M" \
  --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"

Docker Model Runner
How to use unsloth/MiniMax-M3-GGUF with Docker Model Runner:
```
docker model run hf.co/unsloth/MiniMax-M3-GGUF:UD-Q4_K_M
```

Lemonade

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

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull unsloth/MiniMax-M3-GGUF:UD-Q4_K_M

Run and chat with the model

lemonade run user.MiniMax-M3-GGUF-UD-Q4_K_M

List all available models

lemonade list

Hermes Agent

How to use unsloth/MiniMax-M3-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-GGUF:UD-Q4_K_M

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-GGUF:UD-Q4_K_M

Run Hermes

hermes

Atomic Chat

danielhanchen commited on Jun 12

Commit

59a0b9f

verified ·

1 Parent(s): eec7ebb

Upload folder using huggingface_hub

Browse files

Files changed (1) hide show

README.md +73 -73

README.md CHANGED Viewed

@@ -5,81 +5,56 @@ license_name: minimax-community
 license_link: LICENSE
 library_name: transformers
 tags:
-- multimodal
-- moe
-- agent
-- coding
-- video
-base_model:
-- MiniMaxAI/MiniMax-M3
 ---
-# Read our How to [Run MiniMax M3 Guide!](https://unsloth.ai/docs/models/minimax-m3)
-<div>
-  <p style="margin: 0 0 0px 0; margin-top: 0px;">
-    <em>See <a href="https://unsloth.ai/docs/basics/unsloth-dynamic-v2.0-gguf">Unsloth Dynamic 2.0 GGUFs</a> for our quantization benchmarks.</em>
-  </p>
-  <div style="display: flex; gap: 5px; align-items: center; margin-bottom: 0px;">
-    <a href="https://github.com/unslothai/unsloth/">
-      <img src="https://github.com/unslothai/unsloth/raw/main/images/unsloth%20new%20logo.png" width="133">
-    </a>
-    <a href="https://discord.gg/unsloth">
-      <img src="https://github.com/unslothai/unsloth/raw/main/images/Discord%20button.png" width="173">
-    </a>
-    <a href="https://unsloth.ai/docs/models/minimax-m3">
-      <img src="https://raw.githubusercontent.com/unslothai/unsloth/refs/heads/main/images/documentation%20green%20button.png" width="143">
-    </a>
-  </div>
-<div style="margin: 0;">
-<b>EXPERIMENTAL GGUF / support for MiniMax-M3 in llama.cpp:</b>
 </div>
 </div>
-MiniMax-M3 support in llama.cpp is preliminary and not yet in a released build. To run these GGUFs, build llama.cpp from [PR #24523](https://github.com/ggml-org/llama.cpp/pull/24523):
-```bash
-git clone https://github.com/ggml-org/llama.cpp
-cd llama.cpp
-git fetch origin pull/24523/head:minimax-m3
-git checkout minimax-m3
-cmake -B build -DGGML_CUDA=ON
-cmake --build build --config Release -j --target llama-cli llama-server
-```
-Then run a quant. The model is large (~428B params), so offload across GPUs with `-ngl 99` or keep the weights in CPU RAM:
-```bash
-./build/bin/llama-cli -hf unsloth/MiniMax-M3-GGUF:UD-IQ1_M
-```
-Note: MiniMax Sparse Attention is not supported yet, so inference falls back to dense attention.
----
-# MiniMax-M3
-## Run MiniMax-M3 in llama.cpp
-MiniMax-M3 support in llama.cpp is preliminary and not yet in a released build. To run these GGUFs, build llama.cpp from [PR #24523](https://github.com/ggml-org/llama.cpp/pull/24523):
-```bash
-git clone https://github.com/ggml-org/llama.cpp
-cd llama.cpp
-git fetch origin pull/24523/head:minimax-m3
-git checkout minimax-m3
-cmake -B build -DGGML_CUDA=ON
-cmake --build build --config Release -j --target llama-cli llama-server
-```
-Then run a quant. The model is large (~428B params), so offload across GPUs with `-ngl 99` or keep the weights in CPU RAM:
-```bash
-./build/bin/llama-cli \
-  -hf unsloth/MiniMax-M3-GGUF:UD-Q4_K_XL \
-  --jinja -ngl 99 --ctx-size 8192 \
-  -p "Hello, who are you?"
-```
-Note: MiniMax Sparse Attention is not supported yet, so inference falls back to dense attention.
 MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.
@@ -101,6 +76,9 @@ MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters
 | Precision | bfloat16 |
 | Transformers | ≥ 4.52.4 (`trust_remote_code=True`) |
 | License | [MiniMax Community License](LICENSE) |
 ## How to Use
@@ -111,6 +89,28 @@ M3 supports two reasoning modes:
 - **thinking** — for complex reasoning, agentic tasks, and long-horizon collaboration.
 - **non-thinking** — for latency-sensitive scenarios such as chat and code completion.
 ### ModelScope
 You can also get model weights from [ModelScope](https://modelscope.cn/models/MiniMax/MiniMax-M3).
@@ -129,4 +129,4 @@ Please refer to our [Tool Calling Guide](./docs/tool_calling_guide.md).
 ## Contact Us
-Contact us at [model@minimax.io](mailto:model@minimax.io).

 license_link: LICENSE
 library_name: transformers
 tags:
+  - multimodal
+  - moe
+  - agent
+  - coding
+  - video
 ---
+<div align="center">
+  <img width="60%" src="figures/logo.svg" alt="MiniMax">
 </div>
+<hr>
+<div align="center" style="line-height: 1.4; font-size:16px; margin-top: 30px;">
+  Join Our
+  <a href="https://platform.minimaxi.com/docs/faq/contact-us" target="_blank" style="font-size:17px; margin: 2px;">
+    💬 WeChat
+  </a> |
+  <a href="https://discord.com/invite/DPC4AHFCBw" target="_blank" style="font-size:17px; margin: 2px;">
+    🧩 Discord
+  </a>
+  community.
+</div>
+<div align="center" style="line-height: 1.2; font-size:16px;">
+  <a href="https://agent.minimax.io/" target="_blank" style="display: inline-block; margin: 4px;">
+    MiniMax Agent
+  </a> |
+  <a href="https://platform.minimax.io/docs/guides/text-generation" target="_blank" style="display: inline-block; margin: 4px;">
+    ⚡️ API
+  </a> |
+  <a href="https://github.com/MiniMax-AI/cli" style="display: inline-block; margin: 4px;">
+    CLI
+  </a> |
+  <a href="https://www.minimax.io" target="_blank" style="display: inline-block; margin: 4px;">
+    MiniMax Website
+  </a>
+</div>
+<div align="center" style="line-height: 1.2; font-size:16px; margin-bottom: 30px;">
+  <a href="https://huggingface.co/MiniMaxAI" target="_blank" style="margin: 2px;">
+    🤗 Hugging Face
+  </a> |
+  <a href="https://github.com/MiniMax-AI/MiniMax-M3" target="_blank" style="margin: 2px;">
+    🐙 GitHub
+  </a> |
+  <a href="https://www.modelscope.cn/organization/MiniMax" target="_blank" style="margin: 2px;">
+    🤖️ ModelScope
+  </a> |
+  <a href="https://huggingface.co/MiniMaxAI/MiniMax-M3/blob/main/LICENSE" style="margin: 2px;">
+    📄 LICENSE
+  </a>
 </div>
 MiniMax-M3 is a native multimodal model with 1M context. It has ~428B parameters and ~23B activated parameters.
 | Precision | bfloat16 |
 | Transformers | ≥ 4.52.4 (`trust_remote_code=True`) |
 | License | [MiniMax Community License](LICENSE) |
+<p align="center">
+  <img width="100%" src="figures/benchmark.jpeg">
+</p>
 ## How to Use
 - **thinking** — for complex reasoning, agentic tasks, and long-horizon collaboration.
 - **non-thinking** — for latency-sensitive scenarios such as chat and code completion.
+## Local Deployment
+Download the model:
+```bash
+hf download MiniMaxAI/MiniMax-M3 --local-dir MiniMax-M3
+```
+We recommend the following inference frameworks (listed alphabetically) to serve the model:
+### SGLang
+We recommend using [SGLang](https://docs.sglang.io/) to serve MiniMax-M3. Please refer to our [SGLang Deployment Guide](./docs/sglang_deploy_guide.md).
+### vLLM
+We recommend using [vLLM](https://github.com/vllm-project/vllm) to serve MiniMax-M3. Please refer to our [vLLM Deployment Guide](./docs/vllm_deploy_guide.md).
+### Transformers
+We recommend using [Transformers](https://github.com/huggingface/transformers) to serve MiniMax-M3. Please refer to our [Transformers Deployment Guide](./docs/transformers_deploy_guide.md).
 ### ModelScope
 You can also get model weights from [ModelScope](https://modelscope.cn/models/MiniMax/MiniMax-M3).
 ## Contact Us
+Contact us at [model@minimax.io](mailto:model@minimax.io).