Edge & Browser
Small models, WebGPU in the browser, phones and NPUs.
0 of 3 complete
- ▶ Up next12 min+50 XPSmall models: what 0.5B-4B can really doStrengths, limits and good use cases for tiny models, how to evaluate them on your task, prompt and fine-tune them…
- 12 min+50 XPLLMs in the browser with WebGPUHow WebLLM, transformers.js and WASM runtimes work, what WebGPU gives you, memory and download limits, a worker-based…
- Pro13 min+50 XPPhones, NPUs and embedded devicesRunning LLMs on iOS, Android and single-board computers: memory budgets, bandwidth-based speed estimates, thermals…