Trinity Nano Preview is a 26B-parameter (3B active) sparse mixture-of-experts language model featuring 128 experts with 8 active per token. This entry tracks a preview release and capabilities may change before general availability.
Headline benchmark standings and comparison context.
Benchmark updates coming soon
Trinity Nano Preview is not fully available on the API yet. Benchmark results will be published here as soon as rollout is complete. Please check back soon.
No benchmark data yet
No benchmark data is available for this model yet.
