Instructions to use mlx-community/MiniMax-M3.1-Flash-oQ3e-mtp with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use mlx-community/MiniMax-M3.1-Flash-oQ3e-mtp with MLX:

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

from mlx_vlm import load, generate
from mlx_vlm.prompt_utils import apply_chat_template
from mlx_vlm.utils import load_config

# Load the model
model, processor = load("mlx-community/MiniMax-M3.1-Flash-oQ3e-mtp")
config = load_config("mlx-community/MiniMax-M3.1-Flash-oQ3e-mtp")

# Prepare input
image = ["http://images.cocodataset.org/val2017/000000039769.jpg"]
prompt = "Describe this image."

# Apply chat template
formatted_prompt = apply_chat_template(
    processor, config, prompt, num_images=1
)

# Generate output
output = generate(model, processor, formatted_prompt, image)
print(output)

Notebooks
Google Colab
Kaggle
Local Apps Settings
LM Studio

How to use mlx-community/MiniMax-M3.1-Flash-oQ3e-mtp 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-M3.1-Flash-oQ3e-mtp"

Configure the model in Pi

# Install Pi:
npm install -g @earendil-works/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-M3.1-Flash-oQ3e-mtp"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent

How to use mlx-community/MiniMax-M3.1-Flash-oQ3e-mtp 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-M3.1-Flash-oQ3e-mtp"

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-M3.1-Flash-oQ3e-mtp

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use mlx-community/MiniMax-M3.1-Flash-oQ3e-mtp with OpenClaw:

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-M3.1-Flash-oQ3e-mtp"

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 "mlx-community/MiniMax-M3.1-Flash-oQ3e-mtp" \
  --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"

MiniMax-M3.1-Flash-oQ3e-mtp

This model was quantized using oQ (oMLX v0.7.3.dev1) mixed-precision quantization.

A mixed-precision MLX checkpoint of MiniMaxAI/MiniMax-M3.1-Flash, a native multimodal mixture-of-experts model for coding, agentic workflows, computer use and cybersecurity with about 428B total and 23B activated parameters. It takes text, image and video inputs with a context window of up to 1M tokens, and uses MiniMax Sparse Attention throughout the model. It includes the language model, the vision encoder and the bundled DSpark draft in dspark/, which oMLX Lightning MTP uses for speculative decoding.

The effective average is 3.631 bits/weight for the language model and vision encoder, or 3.657 bits/weight including the DSpark draft.

Quantization and Bit Distribution

oQ3e requantizes the routed experts from NVFP4 to affine 3-bit. It keeps MXFP8 for the shared experts, the sparse attention indexer and about a third of the attention projections, and stores the remaining projections, the embeddings and the vocabulary head as affine 3- to 8-bit. The router and the DSpark draft keep their source precision.

Storage format	Logical weights	Share of total	Tensor storage	Effective bits/weight
Affine 3-bit, group 64	413.311B	96.782%	168.405 GiB	3.50
Affine 4-bit, group 64	2.378B	0.557%	1.246 GiB	4.50
Affine 5-bit, group 64	2.460B	0.576%	1.575 GiB	5.50
Affine 6-bit, group 64	0.226B	0.053%	0.171 GiB	6.50
Affine 8-bit, group 64	2.458B	0.576%	2.433 GiB	8.50
MXFP8, group 32	5.496B	1.287%	5.278 GiB	8.25
BF16	0.678B	0.159%	1.262 GiB	16.00
FP32	0.045B	0.010%	0.167 GiB	32.00
Total	427.052B	100%	180.537 GiB	3.631

Storage Breakdown

Component	Logical weights	Storage
Language model	426.375B	192.497 GB / 179.277 GiB
Vision	0.677B	1.354 GB / 1.261 GiB
DSpark draft (MTP)	2.011B	2.302 GB / 2.144 GiB
Total	429.063B	196.152 GB / 182.681 GiB

License

MiniMax Community License, following the source model. See LICENSE. Commercial use has additional conditions in the license, including displaying "Built with MiniMax M3.1-Flash" and obtaining prior written authorization from MiniMax.

Downloads last month: 480

Safetensors

Model size

427B params

Tensor type

U32

BF16

F32

MLX

Hardware compatibility

3-bit

Model tree for mlx-community/MiniMax-M3.1-Flash-oQ3e-mtp

Base model

MiniMaxAI/MiniMax-M3.1-Flash

Quantized

(32)

this model