Comment executer des LLM sur Mac Mini M4 (Llama, Mistral, Phi)

# Download and install Ollama
curl -fsSL https://ollama.com/install.sh | sh

# Verify installation
ollama --version
# ollama version 0.5.4

# Download Llama 3 8B (4.7GB, fits 16GB RAM)
ollama pull llama3:8b

# Download Mistral 7B (4.1GB)
ollama pull mistral:7b

# Download Phi-3 Mini (2.3GB, great for constrained setups)
ollama pull phi3:mini

# Download Llama 3 70B (requires 48GB+ RAM)
ollama pull llama3:70b

# List downloaded models
ollama list
# NAME            SIZE     MODIFIED
# llama3:8b       4.7 GB   2 minutes ago
# mistral:7b      4.1 GB   5 minutes ago
# phi3:mini       2.3 GB   8 minutes ago

# Start an interactive chat session
ollama run llama3:8b

# Example interaction:
# >>> What is the capital of France?
# The capital of France is Paris. It is the largest city in France
# and serves as the country's political, economic, and cultural center.

# The Ollama server starts automatically, listening on localhost:11434

# Query using curl (OpenAI-compatible endpoint)
curl http://localhost:11434/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama3:8b",
    "messages": [
      {"role": "system", "content": "You are a helpful coding assistant."},
      {"role": "user", "content": "Write a Python function to calculate fibonacci numbers."}
    ],
    "temperature": 0.7,
    "max_tokens": 500
  }'

# Native Ollama API endpoint
curl http://localhost:11434/api/generate \
  -d '{
    "model": "llama3:8b",
    "prompt": "Explain quantum computing in 3 sentences.",
    "stream": false
  }'

# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="http://localhost:11434/v1",
    api_key="ollama"  # Ollama doesn't require an API key
)

response = client.chat.completions.create(
    model="llama3:8b",
    messages=[
        {"role": "system", "content": "You are a senior Python developer."},
        {"role": "user", "content": "Write a FastAPI endpoint for user registration."}
    ],
    temperature=0.7,
    max_tokens=1000
)

print(response.choices[0].message.content)

# Create a launchd plist for auto-start on boot
cat <<EOF > ~/Library/LaunchAgents/com.ollama.server.plist
<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE plist PUBLIC "-//Apple//DTD PLIST 1.0//EN"
  "http://www.apple.com/DTDs/PropertyList-1.0.dtd">
<plist version="1.0">
<dict>
    <key>Label</key>
    <string>com.ollama.server</string>
    <key>ProgramArguments</key>
    <array>
        <string>/usr/local/bin/ollama</string>
        <string>serve</string>
    </array>
    <key>RunAtLoad</key>
    <true/>
    <key>KeepAlive</key>
    <true/>
</dict>
</plist>
EOF

# Load the service
launchctl load ~/Library/LaunchAgents/com.ollama.server.plist

# Verify it's running
curl http://localhost:11434/api/tags

# Install dependencies
brew install cmake

# Clone the repository
git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp

# Build with Metal GPU acceleration (Apple Silicon)
mkdir build && cd build
cmake .. -DLLAMA_METAL=ON -DCMAKE_BUILD_TYPE=Release
cmake --build . --config Release -j$(sysctl -n hw.ncpu)

# Verify Metal support
./bin/llama-cli --help | grep metal

# Install huggingface-cli for easy downloads
pip install huggingface_hub

# Download Llama 3 8B Q4_K_M (best quality/speed balance)
huggingface-cli download \
  TheBloke/Llama-3-8B-GGUF \
  llama-3-8b.Q4_K_M.gguf \
  --local-dir ./models

# Download Mistral 7B Q4_K_M
huggingface-cli download \
  TheBloke/Mistral-7B-Instruct-v0.2-GGUF \
  mistral-7b-instruct-v0.2.Q4_K_M.gguf \
  --local-dir ./models

# Download Phi-3 Mini Q4
huggingface-cli download \
  microsoft/Phi-3-mini-4k-instruct-gguf \
  Phi-3-mini-4k-instruct-q4.gguf \
  --local-dir ./models

# Run Llama 3 8B with Metal GPU offloading (all layers)
./build/bin/llama-cli \
  -m ./models/llama-3-8b.Q4_K_M.gguf \
  -ngl 99 \
  -c 4096 \
  -t 8 \
  --temp 0.7 \
  -p "Explain how transformers work in machine learning:"

# Key flags:
# -ngl 99     : Offload all layers to Metal GPU
# -c 4096     : Context window size
# -t 8        : Number of CPU threads (M4 has 10 cores)
# --temp 0.7  : Temperature for sampling

# Start OpenAI-compatible API server
./build/bin/llama-server \
  -m ./models/llama-3-8b.Q4_K_M.gguf \
  -ngl 99 \
  -c 4096 \
  --host 0.0.0.0 \
  --port 8080 \
  --parallel 4

# Test the API
curl http://localhost:8080/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "llama-3-8b",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

# Create a virtual environment
python3 -m venv ~/mlx-env
source ~/mlx-env/bin/activate

# Install MLX and the LLM package
pip install mlx mlx-lm

# Verify installation
python3 -c "import mlx.core as mx; print(mx.default_device())"
# Device(gpu, 0)

# Run Llama 3 8B using mlx-lm CLI
mlx_lm.generate \
  --model mlx-community/Meta-Llama-3-8B-Instruct-4bit \
  --prompt "Write a Python decorator for rate limiting:" \
  --max-tokens 500 \
  --temp 0.7

# Run Mistral 7B
mlx_lm.generate \
  --model mlx-community/Mistral-7B-Instruct-v0.3-4bit \
  --prompt "Explain microservices architecture:" \
  --max-tokens 500

from mlx_lm import load, generate

# Load the model (downloads on first run)
model, tokenizer = load("mlx-community/Meta-Llama-3-8B-Instruct-4bit")

# Generate text
prompt = "Write a bash script to monitor disk usage and send alerts:"
response = generate(
    model,
    tokenizer,
    prompt=prompt,
    max_tokens=500,
    temp=0.7,
    top_p=0.9
)
print(response)

# Streaming generation
from mlx_lm import stream_generate

for token in stream_generate(
    model, tokenizer,
    prompt="Explain Docker networking:",
    max_tokens=300
):
    print(token, end="", flush=True)

# pip install fastapi uvicorn mlx-lm
from fastapi import FastAPI
from fastapi.responses import StreamingResponse
from mlx_lm import load, stream_generate
import json

app = FastAPI()
model, tokenizer = load("mlx-community/Meta-Llama-3-8B-Instruct-4bit")

@app.post("/v1/completions")
async def completions(request: dict):
    prompt = request.get("prompt", "")
    max_tokens = request.get("max_tokens", 256)

    response = ""
    for token in stream_generate(model, tokenizer, prompt=prompt, max_tokens=max_tokens):
        response += token

    return {"choices": [{"text": response}]}

@app.post("/v1/chat/completions")
async def chat(request: dict):
    messages = request.get("messages", [])
    prompt = tokenizer.apply_chat_template(messages, tokenize=False)

    response = ""
    for token in stream_generate(model, tokenizer, prompt=prompt, max_tokens=512):
        response += token

    return {
        "choices": [{
            "message": {"role": "assistant", "content": response}
        }]
    }

# Run: uvicorn server:app --host 0.0.0.0 --port 8000

# Quick formula to estimate memory requirements:
# Memory needed = (Parameters in B * Bits per weight / 8) + context overhead
#
# Example: Llama 3 70B at Q4 quantization
# = (70 * 4 / 8) GB = 35 GB model weights
# + ~4 GB context/overhead
# = ~39 GB total → fits in 48GB Mac Mini M4 Pro
#
# Check current memory usage while running a model:
ollama ps
# NAME          SIZE     PROCESSOR    UNTIL
# llama3:8b     5.1 GB   100% GPU     4 minutes from now