I am curious if there are any plans to add these models to the NVIDIA NIM in the near future.
For context, Ornith-1.0 is a self-improving family of models designed specifically for agentic coding and execution-first workflows.
- 9B Dense
- 31B Dense
- 35B MoE
- 397B MoE (flagship)
According to the release details, the flagship model demonstrates highly competitive performance on code-agent benchmarks, such as SWE-Bench Verified and Terminal-Bench 2.1.