DGX Spark (GH200 480GB) vs H100 80GB SXM5 for Local LLMs
The H100 80GB SXM5 has about 570% more memory bandwidth (3,350 vs 500 GB/s). Batch-1 decode tracks bandwidth closely, so a model that fits both cards should decode roughly 570% faster on the H100 80GB SXM5. The DGX Spark (GH200 480GB) fits more of the catalog at Q4/8K — 66 vs 50 of 69 models (480 vs 80 GB VRAM). Largest model that fits the DGX Spark (GH200 480GB) but not the H100 80GB SXM5: DeepSeek-V4-Pro (861.6B). MSRP is $3,000 for the DGX Spark (GH200 480GB) vs $30,000 for the H100 80GB SXM5. MSRP is a launch list price, not live retail — Amazon prices move; click through for the current price. Not retail-shoppable: H100 80GB SXM5 (datacenter-class; cloud rental is the realistic way to use it). In the Q4/8K head-to-head below (62 shared models), the H100 80GB SXM5 posts the higher tok/s in 62 rows vs 0. Methodology.