Instructions to use majentik/MiniMax-M2.7-TurboQuant-MLX-3bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use majentik/MiniMax-M2.7-TurboQuant-MLX-3bit 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("majentik/MiniMax-M2.7-TurboQuant-MLX-3bit")

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 majentik/MiniMax-M2.7-TurboQuant-MLX-3bit with Pi:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/MiniMax-M2.7-TurboQuant-MLX-3bit"

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": "majentik/MiniMax-M2.7-TurboQuant-MLX-3bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

MLX LM

How to use majentik/MiniMax-M2.7-TurboQuant-MLX-3bit with MLX LM:

Generate or start a chat session

# Install MLX LM
uv tool install mlx-lm
# Interactive chat REPL
mlx_lm.chat --model "majentik/MiniMax-M2.7-TurboQuant-MLX-3bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "majentik/MiniMax-M2.7-TurboQuant-MLX-3bit"
# Calling the OpenAI-compatible server with curl
curl -X POST "http://localhost:8000/v1/chat/completions" \
   -H "Content-Type: application/json" \
   --data '{
     "model": "majentik/MiniMax-M2.7-TurboQuant-MLX-3bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Hermes Agent

How to use majentik/MiniMax-M2.7-TurboQuant-MLX-3bit 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 "majentik/MiniMax-M2.7-TurboQuant-MLX-3bit"

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 majentik/MiniMax-M2.7-TurboQuant-MLX-3bit

Run Hermes

hermes

Atomic Chat

OpenClaw

How to use majentik/MiniMax-M2.7-TurboQuant-MLX-3bit with OpenClaw:

Start the MLX server

# Install MLX LM:
uv tool install mlx-lm
# Start a local OpenAI-compatible server:
mlx_lm.server --model "majentik/MiniMax-M2.7-TurboQuant-MLX-3bit"

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 "majentik/MiniMax-M2.7-TurboQuant-MLX-3bit" \
  --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"

majentik commited on Jul 20

Commit

00a3ea3

verified ·

1 Parent(s): 7fb667b

Card accuracy sweep: honest brand labeling, remove dead links, upstream KV tip

Browse files

Files changed (1) hide show

README.md +2 -9

README.md CHANGED Viewed

@@ -34,7 +34,7 @@ tags:
 # MiniMax-M2.7-TurboQuant-MLX-3bit
-**MLX 3-bit quantized variant of [MiniMaxAI/MiniMax-M2.7](https://huggingface.co/MiniMaxAI/MiniMax-M2.7) with TurboQuant KV-cache compression, optimized for Apple Silicon.**
 ## Overview
@@ -106,7 +106,6 @@ print(response)
 - [MiniMaxAI/MiniMax-M2.7](https://huggingface.co/MiniMaxAI/MiniMax-M2.7) -- Base model
 - [majentik/MiniMax-M2.7-RotorQuant-MLX-3bit](https://huggingface.co/majentik/MiniMax-M2.7-RotorQuant-MLX-3bit) -- RotorQuant MLX 3-bit
 - [majentik/MiniMax-M2.7-TurboQuant-MLX-4bit](https://huggingface.co/majentik/MiniMax-M2.7-TurboQuant-MLX-4bit) -- MLX 4-bit
-- [majentik/MiniMax-M2.7-TurboQuant-MLX-2bit](https://huggingface.co/majentik/MiniMax-M2.7-TurboQuant-MLX-2bit) -- MLX 2-bit
 ## Quant trade-off (MLX lane)
@@ -127,15 +126,9 @@ print(response)
 | Variant | Runtime | Approx size | Use case |
 |---|---|---|---|
-| [RotorQuant](https://huggingface.co/majentik/minimax-m2.7-rotorquant) | runtime modifier | n/a | KV-cache root (weight-agnostic) |
-| [RotorQuant-MLX-2bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-2bit) | mlx-lm | ~885 MB | Apple Silicon, smallest |
 | [RotorQuant-MLX-3bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-3bit) | mlx-lm | ~1.2 GB | Apple Silicon, small |
 | [RotorQuant-MLX-4bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-4bit) | mlx-lm | ~1.7 GB | Apple Silicon balanced |
 | [RotorQuant-MLX-5bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-5bit) | mlx-lm | ~2.1 GB | Apple Silicon, higher fidelity |
-| [RotorQuant-MLX-8bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-8bit) | mlx-lm | ~3.2 GB | Apple Silicon reference |
-| [TurboQuant](https://huggingface.co/majentik/minimax-m2.7-turboquant) | runtime modifier | n/a | KV-cache root (weight-agnostic) |
-| [TurboQuant-MLX-2bit](https://huggingface.co/majentik/minimax-m2.7-turboquant-mlx-2bit) | mlx-lm | ~885 MB | Apple Silicon, smallest |
 | **TurboQuant-MLX-3bit** | mlx-lm | ~1.2 GB | Apple Silicon, small |
 | [TurboQuant-MLX-4bit](https://huggingface.co/majentik/minimax-m2.7-turboquant-mlx-4bit) | mlx-lm | ~1.7 GB | Apple Silicon balanced |
-| [TurboQuant-MLX-5bit](https://huggingface.co/majentik/minimax-m2.7-turboquant-mlx-5bit) | mlx-lm | ~2.1 GB | Apple Silicon, higher fidelity |
-| [TurboQuant-MLX-8bit](https://huggingface.co/majentik/minimax-m2.7-turboquant-mlx-8bit) | mlx-lm | ~3.2 GB | Apple Silicon reference |

 # MiniMax-M2.7-TurboQuant-MLX-3bit
+**MLX 3-bit quantized variant of [MiniMaxAI/MiniMax-M2.7](https://huggingface.co/MiniMaxAI/MiniMax-M2.7) with the legacy TurboQuant KV-cache fork (superseded by upstream llama.cpp KV options), optimized for Apple Silicon.**
 ## Overview
 - [MiniMaxAI/MiniMax-M2.7](https://huggingface.co/MiniMaxAI/MiniMax-M2.7) -- Base model
 - [majentik/MiniMax-M2.7-RotorQuant-MLX-3bit](https://huggingface.co/majentik/MiniMax-M2.7-RotorQuant-MLX-3bit) -- RotorQuant MLX 3-bit
 - [majentik/MiniMax-M2.7-TurboQuant-MLX-4bit](https://huggingface.co/majentik/MiniMax-M2.7-TurboQuant-MLX-4bit) -- MLX 4-bit
 ## Quant trade-off (MLX lane)
 | Variant | Runtime | Approx size | Use case |
 |---|---|---|---|
 | [RotorQuant-MLX-3bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-3bit) | mlx-lm | ~1.2 GB | Apple Silicon, small |
 | [RotorQuant-MLX-4bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-4bit) | mlx-lm | ~1.7 GB | Apple Silicon balanced |
 | [RotorQuant-MLX-5bit](https://huggingface.co/majentik/minimax-m2.7-rotorquant-mlx-5bit) | mlx-lm | ~2.1 GB | Apple Silicon, higher fidelity |
 | **TurboQuant-MLX-3bit** | mlx-lm | ~1.2 GB | Apple Silicon, small |
 | [TurboQuant-MLX-4bit](https://huggingface.co/majentik/minimax-m2.7-turboquant-mlx-4bit) | mlx-lm | ~1.7 GB | Apple Silicon balanced |
+| [TurboQuant-MLX-5bit](https://huggingface.co/majentik/minimax-m2.7-turboquant-mlx-5bit) | mlx-lm | ~2.1 GB | Apple Silicon, higher fidelity |