Skip to content

mesh-brain end-state: one lobe per box — Qwen-only on the Spark GB10, Gemma-only on Jetson Thor 128GB, small-model lobes on Jetson AGX Orin 64GB #112

Description

@OriNachum

The mesh-brain end-state the near-term deployment-shape work builds toward — tracked here so the near-term PR can stay small.

End-state: one lobe per box

Box Lobe it hosts Notes
DGX Spark GB10 (128 GB) Qwen cortex only (sakamakismile/Qwen3.6-27B-Text-NVFP4-MTP) Reclaims the co-residency tax — candidate to return from 128K to the 256K-native solo shape
Jetson AGX Thor 128 GB (sm_110) Gemma senses only (Gemma 4 12B multimodal) Full-context senses instead of the 32K co-resident trim
Jetson AGX Orin 64 GB Small-model lobes (minor-class generate + 0.6B pooling gears) Unvalidated card — per the #108 rule it ships nothing until someone boots one

Where the embedder/reranker/audio gears land in the end-state is part of this issue's design work (they are cheap enough to co-reside almost anywhere).

Path

  1. Near-term (spec being cut now, devague frame in progress): deployment shape becomes a first-class, safely-selectable axis — machine-as-brain (default: one box hosts every lobe it can — not everyone has many machines) vs per-box mesh-brain lobe profiles. First mesh-brain move: Spark drops Gemma senses (keeps cortex + embedder + reranker + audio), Thor drops the Qwen cortex (keeps senses + the rest).
  2. This issue (future PR): specialize all the way down to one lobe per box, per the table above.

Constraints carried forward

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions