Instructions to use mlx-community/MiniMax-M2.1-8bit-gs32 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/MiniMax-M2.1-8bit-gs32 with MLX:

# Make sure mlx-lm is installed
# pip install --upgrade mlx-lm

# Generate text with mlx-lm
from mlx_lm import load, generate

model, tokenizer = load("mlx-community/MiniMax-M2.1-8bit-gs32")

prompt = "Write a story about Einstein"
messages = [{"role": "user", "content": prompt}]
prompt = tokenizer.apply_chat_template(
    messages, add_generation_prompt=True
)

text = generate(model, tokenizer, prompt=prompt, verbose=True)

Transformers

How to use mlx-community/MiniMax-M2.1-8bit-gs32 with Transformers:

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

pipe = pipeline("text-generation", model="mlx-community/MiniMax-M2.1-8bit-gs32", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("mlx-community/MiniMax-M2.1-8bit-gs32", trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained("mlx-community/MiniMax-M2.1-8bit-gs32", trust_remote_code=True)
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps
LM Studio

vLLM

How to use mlx-community/MiniMax-M2.1-8bit-gs32 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "mlx-community/MiniMax-M2.1-8bit-gs32"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "mlx-community/MiniMax-M2.1-8bit-gs32",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/mlx-community/MiniMax-M2.1-8bit-gs32

SGLang

How to use mlx-community/MiniMax-M2.1-8bit-gs32 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 "mlx-community/MiniMax-M2.1-8bit-gs32" \
    --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": "mlx-community/MiniMax-M2.1-8bit-gs32",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "mlx-community/MiniMax-M2.1-8bit-gs32" \
        --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": "mlx-community/MiniMax-M2.1-8bit-gs32",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Pi new

How to use mlx-community/MiniMax-M2.1-8bit-gs32 with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/MiniMax-M2.1-8bit-gs32"

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "mlx-lm": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "mlx-community/MiniMax-M2.1-8bit-gs32"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use mlx-community/MiniMax-M2.1-8bit-gs32 with Hermes Agent:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "mlx-community/MiniMax-M2.1-8bit-gs32"

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 mlx-community/MiniMax-M2.1-8bit-gs32

Run Hermes

hermes

MLX LM

How to use mlx-community/MiniMax-M2.1-8bit-gs32 with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "mlx-community/MiniMax-M2.1-8bit-gs32"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "mlx-community/MiniMax-M2.1-8bit-gs32"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "mlx-community/MiniMax-M2.1-8bit-gs32",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Docker Model Runner
How to use mlx-community/MiniMax-M2.1-8bit-gs32 with Docker Model Runner:
```
docker model run hf.co/mlx-community/MiniMax-M2.1-8bit-gs32
```

mlx-community
/

MiniMax-M2.1-8bit-gs32

Upload

+version https://git-lfs.github.com/spec/v1
+oid sha256:bb122a6064d38f8327a427ce84454554683cf9e5e55cb3cbe1c988459da93383
+size 5335284408

+version https://git-lfs.github.com/spec/v1
+oid sha256:200cf337f350659134c350365f98fc8cbd53063cac2ddcd2bee37de5fa28685e
+size 4328779821

+version https://git-lfs.github.com/spec/v1
+oid sha256:f91fb09e5da94b48dc41853ca726fe344d543a5a7f7c8948fffb095dfa853c33
+size 5335284348

+version https://git-lfs.github.com/spec/v1
+oid sha256:88d963f7a7efb1dc161bd51f08dcae23446eaef89741f45bcf41d2277bb72c42
+size 4278319949

+version https://git-lfs.github.com/spec/v1
+oid sha256:d956655b083a5f97241074c591cf5e71ef8b146898e27f10c4c637e3abb8117d
+size 5335284414

+version https://git-lfs.github.com/spec/v1
+oid sha256:ad7938c5f718736b1e7e7389d1875a0a98429e399814e819452cb2d2cfe45776
+size 4278319941

+version https://git-lfs.github.com/spec/v1
+oid sha256:222e557c62aad8ac2548417eb479f32bfa07002bd2f5a8cc68bda0b4b6909ca8
+size 5335284416

+version https://git-lfs.github.com/spec/v1
+oid sha256:e550da568182f2655f0ef19e761556a41260d91f540b4b4d38ac75ccb7fe020b
+size 4328779817

+version https://git-lfs.github.com/spec/v1
+oid sha256:02ac060686a52a1a5366c47e44a3aea15b7781aad1d207a51abfca5ac9903214
+size 5335284400

+version https://git-lfs.github.com/spec/v1
+oid sha256:b26fe00b19481879bdc57b3216dca558cd34e91e7adc74f6b3bafda638297107
+size 4278319945

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

	@@ -0,0 +1,3 @@

+version https://git-lfs.github.com/spec/v1
+oid sha256:a235cc25e569dad6a8e1eb14242c5d3c588b41f4c5a41ee264d2d35af3f43dc2
+size 4278319939

+version https://git-lfs.github.com/spec/v1
+oid sha256:382e114a56d8a96b9bf9bc2197901ce2b959e029679a67970e4f3910a3d7d6f6
+size 5335284412

+version https://git-lfs.github.com/spec/v1
+oid sha256:18a31d54d2794711194bfd572a434cbf4c73d121060b62b7a4ad8f4ec4bcc289
+size 4328779837