generate()

final result = await RunAnywhere.generate(
  'Explain quantum computing in simple terms',
  LLMGenerationOptions(
    maxTokens: 200,
    temperature: 0.7,
  ),
);

print('Response: ${result.text}');
print('Tokens: ${result.tokensGenerated}');
print('Speed: ${result.tokensPerSecond.toStringAsFixed(1)} tok/s');
print('Latency: ${result.generationTimeMs.toStringAsFixed(0)}ms');

final options = LLMGenerationOptions(
  maxTokens: 256,
  temperature: 0.7,
  topP: 0.95,
  stopSequences: ['END', '###'],
  systemPrompt: 'You are a helpful coding assistant.',
);

final same = LLMGenerationOptions()
  ..maxTokens = 256
  ..temperature = 0.7;

await RunAnywhere.models.register(
  id: 'qwen-cot',
  name: 'Qwen CoT',
  url: 'https://huggingface.co/.../qwen-cot.gguf',
  framework: InferenceFramework.INFERENCE_FRAMEWORK_LLAMA_CPP,
  supportsThinking: true,
);

final result = await RunAnywhere.generate('Solve: 2x + 5 = 15');

if (result.hasThinkingContent()) {
  print('Reasoning: ${result.thinkingContent}');
}
print('Answer: ${result.text}');