Instructions to use SpermAI/SpermLLM-S1-Ministral3-4B with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use SpermAI/SpermLLM-S1-Ministral3-4B with llama-cpp-python:

# !pip install llama-cpp-python

from llama_cpp import Llama

llm = Llama.from_pretrained(
	repo_id="SpermAI/SpermLLM-S1-Ministral3-4B",
	filename="ministral3-3b-bf16.gguf",
)

llm.create_chat_completion(
	messages = "No input example has been defined for this model task."
)

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use SpermAI/SpermLLM-S1-Ministral3-4B with llama.cpp:

Install from brew

brew install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SpermAI/SpermLLM-S1-Ministral3-4B:BF16
# Run inference directly in the terminal:
llama-cli -hf SpermAI/SpermLLM-S1-Ministral3-4B:BF16

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama-server -hf SpermAI/SpermLLM-S1-Ministral3-4B:BF16
# Run inference directly in the terminal:
llama-cli -hf SpermAI/SpermLLM-S1-Ministral3-4B:BF16

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf SpermAI/SpermLLM-S1-Ministral3-4B:BF16
# Run inference directly in the terminal:
./llama-cli -hf SpermAI/SpermLLM-S1-Ministral3-4B:BF16

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf SpermAI/SpermLLM-S1-Ministral3-4B:BF16
# Run inference directly in the terminal:
./build/bin/llama-cli -hf SpermAI/SpermLLM-S1-Ministral3-4B:BF16

Use Docker

docker model run hf.co/SpermAI/SpermLLM-S1-Ministral3-4B:BF16

LM Studio
Jan
Ollama
How to use SpermAI/SpermLLM-S1-Ministral3-4B with Ollama:
```
ollama run hf.co/SpermAI/SpermLLM-S1-Ministral3-4B:BF16
```

Unsloth Studio

How to use SpermAI/SpermLLM-S1-Ministral3-4B with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SpermAI/SpermLLM-S1-Ministral3-4B to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for SpermAI/SpermLLM-S1-Ministral3-4B to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for SpermAI/SpermLLM-S1-Ministral3-4B to start chatting

How to use SpermAI/SpermLLM-S1-Ministral3-4B with Pi:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SpermAI/SpermLLM-S1-Ministral3-4B:BF16

Configure the model in Pi

# Install Pi:
npm install -g @mariozechner/pi-coding-agent
# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "SpermAI/SpermLLM-S1-Ministral3-4B:BF16"
        }
      ]
    }
  }
}

Run Pi

# Start Pi in your project directory:
pi

Hermes Agent new

How to use SpermAI/SpermLLM-S1-Ministral3-4B with Hermes Agent:

Start the llama.cpp server

# Install llama.cpp:
brew install llama.cpp
# Start a local OpenAI-compatible server:
llama-server -hf SpermAI/SpermLLM-S1-Ministral3-4B:BF16

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 SpermAI/SpermLLM-S1-Ministral3-4B:BF16

Run Hermes

hermes

Docker Model Runner
How to use SpermAI/SpermLLM-S1-Ministral3-4B with Docker Model Runner:
```
docker model run hf.co/SpermAI/SpermLLM-S1-Ministral3-4B:BF16
```

Lemonade

How to use SpermAI/SpermLLM-S1-Ministral3-4B with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull SpermAI/SpermLLM-S1-Ministral3-4B:BF16

Run and chat with the model

lemonade run user.SpermLLM-S1-Ministral3-4B-BF16

List all available models

lemonade list

SpermLLM Ministral3 3B

A fine-tuned version of Ministral-3-3B-Instruct-2512 trained with Unsloth on a carefully curated mix of SOTA reasoning and instruction-following datasets.

Optimized for math, code, science, and general reasoning — competitive with models 2-3x its size.

Model Details

Property	Value
Base Model	mistralai/Ministral-3-3B-Instruct-2512
Model Type	Causal Language Model (Decoder-only)
Parameters	3.84B
Trainable Parameters	135M (3.39% via LoRA)
Architecture	Mistral with Sliding Window Attention
Context Length	8,192 tokens
Training Hardware	NVIDIA B200 (180GB VRAM)
Training Framework	Unsloth + TRL SFTTrainer
Precision	BFloat16
Quantization	4-bit QLoRA during training
License	Apache 2.0

This AI is (sorta SOTA) for it's size, as it can create multiple stuff without errors, this is our latest model

Downloads last month: 12

GGUF

Model size

4B params

Architecture

mistral3

Hardware compatibility

16-bit

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for SpermAI/SpermLLM-S1-Ministral3-4B

Base model

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

Quantized

mistralai/Ministral-3-3B-Instruct-2512

Quantized

(38)

this model