Skip to content
MCS · Rigs · Compare

Side-by-side, with the numbers that matter.

Two rigs, one table. Higher numbers win in cobalt; TDP and price flip.

0 of 37 fields comparable

⇄ swap sides
SpecTesla OptimusNVIDIA HGX B200
AI StackTesla FSD-derived end-to-end neural networks (vision-only)—
Battery KWH2.3—
Fp16 Bf16 Pflops—36
FP32 TFLOPS—600
FP4 Pflops Dense—72
FP4 Pflops Sparse—144
FP64 TFLOPS—296
FP8 FP6 Pflops—72
Fremont Line Capacity Robots PER Year1,000,000—
Fremont Status Q2 2026S/X lines decommissioned; Optimus lines being installed—
Gen2 Announcement Date2023-12-13—
Gen2 Hand DOF11—
Gen2 Height CM173—
Gen2 Neck DOF2—
Gen2 Total DOF Unverified28—
Gen2 Walking Speed Boost PCT30—
Gen2 Weight KG57—
Gen2 Weight Reduction KG10—
Gen3 Announcement QuarterQ1 2026—
Gen3 Forearm Actuators25—
Gen3 Hand DOF22—
Gen3 Payload KG20—
Gen3 Production Target Supersededsummer 2026—
Gen3 Total Actuators PER Robot50—
Gen3 Unveil Statusnot unveiled as of 2026-09-23 (Tesla North)—
Gpus—8
Int8 Pops—72
Networking Bandwidth TB S—0.8
Nvlink Generation—5
Nvlink GPU TO GPU TB S—1.8
Payload PER Hand KG9—
Public Sale Targetend of 2027 (Musk at Davos, 2026-01-22)—
Runtime Hours Light Duty8—
Status Checked2026-09-24—
Total HBM GB—1,400
Total Nvlink Bandwidth TB S—14.4
Walking Speed KM H8—