RTX Spark 128GB Windows ARM: FULL MiniMax H3 in ComfyUI + CUDA Memory Limit

Hi NVIDIA team,

I am considering purchasing an NVIDIA RTX Spark 128GB Windows system specifically for local ComfyUI workloads.

I need confirmation about one exact configuration:

MiniMax H3 FULL/native:

  • minimax_h3_fl2va_bf16 (~66.3 GB)
  • Qwen3-VL-32B BF16 text encoder (~51.5 GB)
  • native non-quantized video VAE
  • native audio VAE
  • no INT8
  • no FP8
  • no NVFP4
  • no GGUF

Questions:

  1. Has NVIDIA tested or validated this exact FULL H3 configuration on ONE RTX Spark 128GB under Windows 11 ARM?

  2. If yes, what was the peak unified/CUDA memory usage?

  3. What is the practical maximum CUDA/PyTorch memory available to one process on a 128GB RTX Spark Windows system?
    Can one workload reliably use 100GB, 110GB, 115GB or 120GB?

  4. Is staged loading/offloading in ComfyUI expected to make this FULL configuration feasible, or is the available Windows memory budget too small?

I am specifically asking about the full native models above, not quantized versions.

Thank you.