Instructions to use hunterbown/Ministral-3-14B-Reasoning-2512-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use hunterbown/Ministral-3-14B-Reasoning-2512-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("hunterbown/Ministral-3-14B-Reasoning-2512-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 hunterbown/Ministral-3-14B-Reasoning-2512-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 "hunterbown/Ministral-3-14B-Reasoning-2512-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": "hunterbown/Ministral-3-14B-Reasoning-2512-MLX-4bit"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use hunterbown/Ministral-3-14B-Reasoning-2512-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 "hunterbown/Ministral-3-14B-Reasoning-2512-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 hunterbown/Ministral-3-14B-Reasoning-2512-MLX-4bit

Run Hermes

hermes

MLX LM

How to use hunterbown/Ministral-3-14B-Reasoning-2512-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 "hunterbown/Ministral-3-14B-Reasoning-2512-MLX-4bit"

Run an OpenAI-compatible server

# Install MLX LM
uv tool install mlx-lm
# Start the server
mlx_lm.server --model "hunterbown/Ministral-3-14B-Reasoning-2512-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": "hunterbown/Ministral-3-14B-Reasoning-2512-MLX-4bit",
     "messages": [
       {"role": "user", "content": "Hello"}
     ]
   }'

Ministral-3-14B-Reasoning-2512-MLX-4bit

This is a 4-bit quantized MLX version of Ministral-3-14B-Reasoning-2512 for Apple Silicon Macs.

Known Limitations

Vision capabilities are NOT working in this MLX conversion. The model runs text-only inference successfully, but the Pixtral vision encoder does not properly process images. This appears to be a known issue with mlx-vlm's Mistral3/Pixtral support. Use this model for text-only tasks until mlx-vlm fixes Mistral3 vision support.

Model Details

Property	Value
Original Model	mistralai/Ministral-3-14B-Reasoning-2512
Parameters	14B (13.5B LLM + 0.4B Vision)
Quantization	4-bit (group size 64)
Size	~7.9 GB
Framework	MLX
Context Length	256K tokens
Vision Support	Not working (see above)

What Works

Text generation: Full reasoning capabilities with [THINK] tags
Multilingual: 11 languages supported
Function calling: Native tool use support
Performance: ~45-50 tokens/sec on Apple Silicon

What Doesn't Work

Vision/Image understanding: The Pixtral vision encoder is included but does not properly process images due to mlx-vlm compatibility issues

Requirements

macOS 15.0+ (Sequoia)
Apple Silicon Mac (M1/M2/M3/M4)
16GB+ unified memory recommended
Python 3.10+

Installation

pip install mlx-vlm

Usage (Text-Only)

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

# Load model
model, processor = load("hunterbown/Ministral-3-14B-Reasoning-2512-MLX-4bit")

# Text inference with reasoning
prompt = apply_chat_template(
    processor,
    config=model.config,
    prompt="Solve this step by step: What is 15% of 240?"
)
output = generate(model, processor, prompt, max_tokens=500)
print(output.text)

Performance

On Apple Silicon (M-series):

Generation speed: ~45-50 tokens/sec
Peak memory: ~8.5 GB
Prompt processing: ~220 tokens/sec

Conversion Details

Converted using mlx-vlm:

python -m mlx_vlm.convert \
  --hf-path mistralai/Ministral-3-14B-Reasoning-2512 \
  --mlx-path ./ministral-3-14b-reasoning-4bit \
  -q --q-bits 4 --q-group-size 64

Alternatives for Vision

If you need vision capabilities, consider:

GGUF versions with llama.cpp
Wait for mlx-vlm to fix Mistral3 vision support

License

Apache 2.0 (same as original model)

Credits

Original model by Mistral AI
MLX conversion using mlx-vlm
Quantized by @hunterbown

Downloads last month: 149

MLX

Hardware compatibility

4-bit

Model tree for hunterbown/Ministral-3-14B-Reasoning-2512-MLX-4bit

Base model

mistralai/Ministral-3-14B-Base-2512

Finetuned

mistralai/Ministral-3-14B-Reasoning-2512

Quantized

(33)

this model