VLM · local, aws-gpu
Gemma 4
Gemma 4 is the perception/tool VLM path for robot camera streams, sim frames, and multimodal workflow glue.
Runtime Target
Start with VLM frame analysis around MuJoCo or real robot cameras; use cloud when local memory is not enough.
Plan
PRO
Provider
aws-batch
Accelerator
nvidia-l4-or-a10g
Simulator
mujoco-camera-stream
Embodiment
robot camera stream
Placement
local-or-cloud
Status
Working Now
Browser MuJoCo demos, model catalog, paid gating, autoscaling planner, and API control-plane responses.
Ready To Deploy
AWS CDK scale-to-zero Batch infrastructure shape for GPU and CPU queues.
Not Live Yet
Local/smaller-model paths are plausible; hosted GPU execution is control-plane-only until worker images are connected.