Qwen 3 32B

pip install -U transformers

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="Qwen/Qwen3-32B")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

pip install -U transformers

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen3-32B")
model = AutoModelForCausalLM.from_pretrained("Qwen/Qwen3-32B", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

curl -LsSf https://llama.app/install.sh | sh

# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Qwen/Qwen3-32B-GGUF:Q4_K_M

# Run inference directly in the terminal:
llama cli -hf Qwen/Qwen3-32B-GGUF:Q4_K_M

winget install llama.cpp

# Start a local OpenAI-compatible server with a web UI:
llama serve -hf Qwen/Qwen3-32B-GGUF:Q4_K_M

# Run inference directly in the terminal:
llama cli -hf Qwen/Qwen3-32B-GGUF:Q4_K_M

# 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 Qwen/Qwen3-32B-GGUF:Q4_K_M

# Run inference directly in the terminal:
./llama-cli -hf Qwen/Qwen3-32B-GGUF:Q4_K_M

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 Qwen/Qwen3-32B-GGUF:Q4_K_M

# Run inference directly in the terminal:
./build/bin/llama-cli -hf Qwen/Qwen3-32B-GGUF:Q4_K_M

docker model run hf.co/Qwen/Qwen3-32B-GGUF:Q4_K_M

ollama run qwen3:32b

ollama run hf.co/Qwen/Qwen3-32B-GGUF:Q4_K_M

# Install llama.cpp:
brew install llama.cpp

# Start a local OpenAI-compatible server:
llama serve -hf Qwen/Qwen3-32B-GGUF:Q4_K_M

# Install Pi:
npm install -g @earendil-works/pi-coding-agent

# Add to ~/.pi/agent/models.json:
{
  "providers": {
    "llama-cpp": {
      "baseUrl": "http://localhost:8080/v1",
      "api": "openai-completions",
      "apiKey": "none",
      "models": [
        {
          "id": "Qwen/Qwen3-32B-GGUF:Q4_K_M"
        }
      ]
    }
  }
}

# Start Pi in your project directory:
pi

npx -y node-llama-cpp chat hf:Qwen/Qwen3-32B-GGUF:Q4_K_M

npx -y node-llama-cpp inspect estimate hf:Qwen/Qwen3-32B-GGUF:Q4_K_M

docker model run hf.co/Qwen/Qwen3-32B-GGUF:Q4_K_M

curl https://localai.io/install.sh | sh

# Load and run the model:
local-ai run huggingface://Qwen/Qwen3-32B-GGUF/{{GGUF_FILE}}

# Pull the image:
docker pull localai/localai:latest-cpu

# Load and run the model:
docker run -p 8080:8080 --name localai -v $PWD/models:/build/models localai/localai:latest-cpu huggingface://Qwen/Qwen3-32B-GGUF/{{GGUF_FILE}}

# Download Lemonade from https://lemonade-server.ai/

lemonade pull Qwen/Qwen3-32B-GGUF:Q4_K_M

lemonade run user.Qwen3-32B-GGUF-Q4_K_M

lemonade list

# Install llama.cpp:
brew install llama.cpp

# Start a local OpenAI-compatible server:
llama serve -hf Qwen/Qwen3-32B-GGUF:Q4_K_M

# 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 Qwen/Qwen3-32B-GGUF:Q4_K_M

hermes

# Install llama.cpp:
brew install llama.cpp

# Start a local OpenAI-compatible server:
llama serve -hf Qwen/Qwen3-32B-GGUF:Q4_K_M

# 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 "Qwen/Qwen3-32B-GGUF:Q4_K_M" \
  --custom-provider-id llama-cpp \
  --custom-compatibility openai \
  --custom-text-input \
  --accept-risk \
  --skip-health

openclaw agent --local --agent main --message "Hello from Hugging Face"