Run DeepSeek-V4-Flash at full 1M context AND two MiniMax H3 video instances on the same two DGX Sparks. Benchmarked C1-C6.
Distributed image and video generation in ComfyUI for two NVIDIA DGX Sparks.
MiniMax-H3 multi-GPU inference acceleration: ~12x on 8x RTX 6000D (step distillation + SageAttention2 + Cache-DiT + torch.compile, TP2+Ulysses4 on sglang)
MiniMax-H3 33B audio+video DiT accelerated 1.54x on a single NVIDIA DGX Spark (GB10, sm_121): NVIDIA Sol-Engine FirstBlockCache + batched VAE decode ported to single-GPU ComfyUI, Sol-Attn patched for compute 12.1, kijai Triton INT8/TMA kernels. Benchmarks, charts, one-shot installer, agent recipe.
Helpful Tools for the Nvidia DGX Spark AI Personal Supercomputer
MiniMax-H3 on single DGX Spark: keys Sol-Engine ports + Heretic TE + Spectrum/Sage speed + 0.5MP upscaler finish. Formal bench included.
2x DGX Spark recipe for LibertAIDAI/GLM-5.3-Flash-NVFP4 (NVFP4, Ray TP=2, multimodal)
Measured SM121 compatibility recipe for MiniMax H3 FL2VA on one NVIDIA DGX Spark with vLLM-Omni and online FP8.
Bleeding-edge ComfyUI for NVIDIA DGX Spark (GB10/Blackwell/sm_121a). CUDA 13 + SageAttention v3 (sm_121a) + NVFP4 + 14 custom-node packs + Flux 2 Dev / LTX 2.3 22B / ACE-Step v1.5 XL Turbo pre-bundled with abliterated text-encoder paths.
