apiVersion: lumbridge/v1
kind: Scene
metadata:
  name: nemotron
  version: 1
  description: "The assistant stack with NVIDIA Nemotron 3.5 Lightning 30B-A3B in place of the Qwen MoE brain — the A/B candidate for replacing `brain`."
  author: karti
  tags: [assistant, voice, "downstream", candidate, nemotron]

# Deliberately the assistant stack with ONE substitution. `brain-nemotron` takes :8001
# in place of `brain`, so the two are mutually exclusive by construction — and
# that is also what the hardware wants: 68GB is already spoken for with brain
# up, and two MoE engines would each spike during KV profiling.
#
# Keeping ears/voice/embed/ocr identical is the point. The only variable
# between the primary scene and this scene is which brain answers :8001, so an eval run
# against one is comparable to an eval run against the other.
#
# ORDER MATTERS, same rule as the primary scene: whatever holds :8001 comes up
# first and alone. brain's KV-profiling spike is not bounded by
# gpu-memory-utilization and this engine is unproven on the box, so it gets
# the empty machine.
models:
  - brain-nemotron
  - ears
  - voice
  - embed
  - ocr
  # The eye, added 2026-08-12. Cosmos3-Edge is BF16-only and cannot be
  # quantized, so it costs a real 12GB that the other slots do not.
  - eye

budget_gb: 100
activation:
  order: listed
  wait_healthy: true