Instructions to use Java-dmd/Ministral-3-3B-Instruct-GGUF with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- llama.cpp
How to use Java-dmd/Ministral-3-3B-Instruct-GGUF with llama.cpp:
Install (macOS, Linux)
curl -LsSf https://llama.app/install.sh | sh # Start a local OpenAI-compatible server with a web UI: llama serve -hf Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M
Install from WinGet (Windows)
winget install llama.cpp # Start a local OpenAI-compatible server with a web UI: llama serve -hf Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: llama cli -hf Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M
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 Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: ./llama-cli -hf Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M
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 Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M # Run inference directly in the terminal: ./build/bin/llama-cli -hf Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M
Use Docker
docker model run hf.co/Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M
- LM Studio
- Jan
- Ollama
How to use Java-dmd/Ministral-3-3B-Instruct-GGUF with Ollama:
ollama run hf.co/Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M
- Unsloth Desktop
- Docker Model Runner
How to use Java-dmd/Ministral-3-3B-Instruct-GGUF with Docker Model Runner:
docker model run hf.co/Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M
- Lemonade
How to use Java-dmd/Ministral-3-3B-Instruct-GGUF with Lemonade:
Pull the model
# Download Lemonade from https://lemonade-server.ai/ lemonade pull Java-dmd/Ministral-3-3B-Instruct-GGUF:Q4_K_M
Run and chat with the model
lemonade run user.Ministral-3-3B-Instruct-GGUF-Q4_K_M
List all available models
lemonade list
- Atomic Chat
Model Details
Ministral-3-3B-Instruct spécialisé dans la correction d'adresses postales françaises
Model Description
Il s'agit d'une version quantifiée au format GGUF (Q4_K_M) du modèle Ministral-3-3B-Instruct, entraîné et personnalisé à l'aide d'Unsloth Studio. La conversion a été réalisée de manière chirurgicale à partir des poids fusionnés (Merged Model) pour assurer une parfaite fidélité des calculs tout en conservant le support de l'architecture spécifique et du Tokenizer du modèle d'origine.
- Architecture de base : Ministral-3-3B
- Format final : GGUF (Quantization Q4_K_M)
- Langues supportées : Français, Anglais (et multilingue)
Model Sources [optional]
- Downloads last month
- 115
Hardware compatibility
Log In to add your hardware
4-bit
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support