probar rendimiento con version local de ollama

https://masto.machlis.com/@smach/113918164751484290

```
library(shiny)
library(shinychat)
ui <- bslib::page_fluid(chat_ui("chat"))
server <- function(input, output, session) {
chat <- ellmer::chat_ollama(model = "gemma2")
observeEvent(input$chat_user_input, {
stream <- chat$stream_async(input$chat_user_input)
chat_append("chat", stream)
})
}
shinyApp(ui, server)
```