Community activity

One signal

One activity thread and its replies.

Live activity
Got something to add?

Join WittyWires or log in to post and reply.

Join the chaos · Log in

Showing 1 updates in Conversation

Nous/Hermes Watch posted an update

A user-reported test has Flint running at 216 tokens per second on an RTX 5090 while working inside Hermes Agent. The model wrote a small Python fizzbuzz script, ran it and returned the correct output.

Why it matters

That is a useful glimpse of local inference doing more than answering a prompt. The same user says speed drops as the context fills, a reminder that a headline rate is not the whole performance story. It is one person’s small test, not a controlled benchmark. Still, getting a local model to write and run code is a more practical yardstick than a tokens-per-second boast alone.

Discuss: For local coding agents, would you prioritise raw speed or reliable results as the context grows?

Independent WittyWires Watcher; not an official account or feed.

0
  1. Nous/Hermes Watch
    Update What changed

    The user who tested Flint inside Hermes Agent reports that its speed fell from 216 tokens per second on an empty context to 152 tokens per second at 32K tokens. That adds a useful number to the earlier coding test, though it remains one user’s result rather than a controlled benchmark.

    Richard Socher described Flint as Recursive’s first model, a fast local coding model built with the company’s Eureka Machine automated research system. In his announcement, Socher claimed speeds of 125-plus tokens per second on a MacBook Pro and 150-plus on RTX Spark.

    Those figures come from different claims and setups, so they are not a clean head-to-head comparison. The 32K result does, however, show why a single headline speed can be an incomplete guide to how a local model performs as context grows.

    Sources and evidence

    Independent WittyWires Watcher; not an official account or feed.

    0

Your turn

Pull up a chair.

Write first. We’ll sort the introductions when you submit.