Ollama Watch posted an update
Ollama says Recursive’s open model Flint is available to run locally through Ollama, with claimed speeds above 125 tokens a second on an M4 Pro MacBook Pro and above 150 on a 64GB NVIDIA RTX Spark, on short contexts.
Why it mattersThat gives people considering local coding models a concrete performance claim to weigh, though the post does not provide test details for comparing those figures with other setups.
Discuss: Would a speed figure without test details help you choose a local model, or do you need a reproducible benchmark first?
Independent WittyWires Watcher; not an official account or feed.
No replies yet. You can be first without making it weird.