Instructions to use pipenetwork/MiniMax-M3-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use pipenetwork/MiniMax-M3-MLX-4bit 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("pipenetwork/MiniMax-M3-MLX-4bit")

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)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use pipenetwork/MiniMax-M3-MLX-4bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/MiniMax-M3-MLX-4bit"

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": "pipenetwork/MiniMax-M3-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use pipenetwork/MiniMax-M3-MLX-4bit 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 "pipenetwork/MiniMax-M3-MLX-4bit"

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 pipenetwork/MiniMax-M3-MLX-4bit

Run Hermes

hermes

OpenClaw new

How to use pipenetwork/MiniMax-M3-MLX-4bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "pipenetwork/MiniMax-M3-MLX-4bit"

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 "pipenetwork/MiniMax-M3-MLX-4bit" \
  --custom-provider-id mlx-lm \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

Run OpenClaw

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

MLX LM

How to use pipenetwork/MiniMax-M3-MLX-4bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "pipenetwork/MiniMax-M3-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "pipenetwork/MiniMax-M3-MLX-4bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "pipenetwork/MiniMax-M3-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

pipenetwork commited on Jun 13

Commit

17727e0

verified ·

1 Parent(s): 57d6312

Add files using upload-large-folder tool

Browse files

Files changed (16) hide show

model-00001-of-00057.safetensors +3 -0
model-00004-of-00057.safetensors +3 -0
model-00008-of-00057.safetensors +3 -0
model-00013-of-00057.safetensors +3 -0
model-00016-of-00057.safetensors +3 -0
model-00019-of-00057.safetensors +3 -0
model-00021-of-00057.safetensors +3 -0
model-00030-of-00057.safetensors +3 -0
model-00033-of-00057.safetensors +3 -0
model-00036-of-00057.safetensors +3 -0
model-00039-of-00057.safetensors +3 -0
model-00040-of-00057.safetensors +3 -0
model-00045-of-00057.safetensors +3 -0
model-00051-of-00057.safetensors +3 -0
model-00052-of-00057.safetensors +3 -0
model-00054-of-00057.safetensors +3 -0

+version https://git-lfs.github.com/spec/v1
+oid sha256:c92e53ccbca581f90fc4b64cd314f5fb6db574edee5f5072c0d22c840b49071b
+size 5316614427

+version https://git-lfs.github.com/spec/v1
+oid sha256:9cbd5dd219cbca61753742200128b23db449acc2458089a7d53bbd32b43da26e
+size 4169791125

+version https://git-lfs.github.com/spec/v1
+oid sha256:75f41ea5ab1ac0575f0097acb167716f1dbbd1c2b162d3cb56015d7b7795b79d
+size 4169791143

+version https://git-lfs.github.com/spec/v1
+oid sha256:c6b7eee8217d1348a1536c4d16510135932e9e4268d0999647697f907c2d2511
+size 4169791145

+version https://git-lfs.github.com/spec/v1
+oid sha256:62ea0104b1bdcc5d0dac88026c397d4681283f06dc4798ffc249dc4e5874f108
+size 4169791119

+version https://git-lfs.github.com/spec/v1
+oid sha256:d02929a5d39ac270a2c5ba92ccc3b4c1d0c218061c5bd0a0c21150a8d385041d
+size 4169791191

+version https://git-lfs.github.com/spec/v1
+oid sha256:27941afde42a099cd111af8c09a7e222673b46773b5269f1daba3793fd9f5268
+size 4169791147

+version https://git-lfs.github.com/spec/v1
+oid sha256:b879c1a7f9d4c6ddd751916cfdb8d5e0e350af62992a1f77b9ae507992df0c55
+size 4169791187

+version https://git-lfs.github.com/spec/v1
+oid sha256:46f81bead105213f929f9e431d9ae828bf758be5df60d93668423fbbe88a0b85
+size 4169791131

+version https://git-lfs.github.com/spec/v1
+oid sha256:60ca2ebbd586936102475a8834c7177449ba0ac13947d6d1eb3e6d310f6018ba
+size 4169791149

	@@ -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:b9673f97cf8812d060464e39e2a53cf45064ee196b55a8987758fd5bcd560143
+size 4169791173

+version https://git-lfs.github.com/spec/v1
+oid sha256:59a0ae56bfe91a4f071ba0d099f532175ab657d6b5577cac59a5112bc9dc1924
+size 4169791167

+version https://git-lfs.github.com/spec/v1
+oid sha256:2ba7e2622e606844b95d8675c3c252ee2a35abb590ce9d9beb44689ba7c6d979
+size 4169791163

+version https://git-lfs.github.com/spec/v1
+oid sha256:74b9fbb4a38617808d0f567b0bd8ebeeb63f3e538f456f06285a8df65afe8521
+size 4169791109