B300 Inference Throughput Hits Multiple Times DeepSeek's

teortaxesTex · x · 2026-07-08

The B300 NVL72 paired with Dynamo achieves an 8K context per card at 80 tps, while DeepSeek using DSpark reaches about 1K context at the same 80 tps. If DeepSeek utilizes the H800 or 950 series, the performance-per-watt gap is at least 4x, though they remain roughly on par in terms of capital expenditure per dollar.

Original post →

More from Infra

Infra channel →