NVIDIA · 141GB · 2 reports
Run models on your NVIDIA H200? Add your numbers.
Your coding agent can run a speed test on your machine and send it here with a free account. Or paste a result you've already posted.
These reports mix GPU counts and memory setups, so a model listed here may have needed extra cards or CPU offloading. The calculator estimates which models fit in 141 GB of VRAM.
User reports DeepSeek V4 Flash with DSpark speculative decoding on an HGX-H200 with 4 GPUs at TP=4 via SGLang. Setup compares the marlin and flashinfer MoE backends. DSpark is faster than EAGLE: 3.2x at bs=1 and +46% throughput at bs=24. The user reports TTFT and accept length benchmarks.
User pretrained a 500M parameter LLM and a 330M image generator from scratch on 8xH200 from modal.com. The total cost was $800, and GGUF weights are included. User mentions pretraining a 1B model next.
Get a weekly email of new NVIDIA H200 reports and newly released models that fit it.
Email me new reports