Better engineering with SLMs with Rachel-Lee Nabors скачать в хорошем качестве

Better engineering with SLMs with Rachel-Lee Nabors

Most teams reach for foundation models by default — even when they’re energetically wasteful and slow. This talk shows how Small Language Models (SLMs) deliver faster response times, offline capability, local-first privacy, and dramatically lower costs using 10–30× fewer resources. 02:22 The real costs of frontier models: security, latency, business, and environmental impact 04:42 Production ≠ feature chasing: why “do everything” models aren’t always right 05:32 When to use small language models (Gemma, Qwen) vs frontier models 06:51 Model size & memory basics + quantization for deployment 08:14 A 4-step framework to choose the best model for the job 10:04 Deployment principle: keep the model near the data 11:39 Local vs remote vs hybrid: how to decide based on offline, security, frequency, battery 13:42 Three local strategies: host it, use device models, deliver it to the device 16:21 Build your own local agent: Ollama + Qwen 3 (4B) + Goose (MCP tools) 17:24 On-device in the browser: Chrome’s Prompt API + live demo Thank you to all our partner to make this happen! A big thanks to our gold sponsors for believing in us: Uphold: Founded in 2013, Uphold is a digital wallet and trading platform that makes cryptocurrencies and other assets affordable and accessible to everyone. With coverage of 300+ assets, Uphold allows users to move seamlessly between digital and traditional currencies, enabling borderless access to financial services you can’t get through your bank. Their Anything-to-Anything interface lets anyone fund, trade, or send money globally in just one tap. Check it here: https://uphold.com Datalinks: DataLinks recognizes the importance of nurturing the AI ecosystem. They bring ontologies and knowledge graphs to Lisbon AI, redefining data engineering and shaping the future of Agentic Workflows and Vertical Search. Discover how scattered data can be unified and linked to power your agents and backends, all with a single click and some prompts: https://datalinks.com/ Follow Rachel: https://x.com/rachelnabors Follow us on X: https://x.com/lisbonai_ Follow us on LinkedIn:   / lisbon-ai   Opening music: ‪@NIN‬​