llamaperf
Oct 17, 2026
Throughput
0.7 t/s gen
Quant
FP8 (FP8)
System RAM
128 GB

Summary

User reports MiMo 2.6 Pro at 0.646 t/s on a Jetson AGX Thor 128GB. Setup is FP8 weights of about 566GB read from disk mid-inference, with experts streamed through 128GB of unified memory. The user notes the model technically loaded and ran, and that every decoder layer, routed expert and SSD read was traced and replayable step by step.

Compare this run

Medians of plain runs: one device, one request, no speculative decoding, the whole model in the device's memory. The report above is one setup, so read it beside them and not as one of them.

Models most run on the NVIDIA Jetson AGX Thor 128GB

Bars are medians on one scale, 0 to 36.7 tokens/s. Press ▶ to watch text arrive at a row's speed.

Everything reported on the NVIDIA Jetson AGX Thor 128GB →Every Mimo 2.6 report →Estimate Mimo 2.6 on this card →