Expired50% confidenceBenchmarkExact time
On the DeepSeek V4 Pro workload, with an interaction target of 160 tokens/second per user, the per-megawatt AI factory throughput of Vera Rubin-NVL72 is up to 30 times higher than that of GB300-NVL72.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/14/2026
First Seen
This claim has expired. It is kept for the record and no longer describes the current state.
Valid until: 10/28/2026(expired)
Sources
Related Entities
Related Claims
UnverifiedUsing NVIDIA B300 chips in a 1-megawatt data center can achieve a total throughput of approximately 450,000 tokens/s, which at 340 tokens/s per user amounts to approximately 1,324 concurrent active users.74% similarUnverifiedThe decode unit of DeepSeek V3 uses 144-card EP, amortizing the weight load overhead across large batches and freeing up GPU memory to increase batch size.73% similarUnverifiedIn the DeepSeek V1 era, each incremental token required nearly 400 KB of KV cache, which dropped to 48 KB in V3.2.73% similarUnverifiedDeepSeek-V3 has a total of 685B parameters, and even after Q4 quantization its size still exceeds 400GB.72% similarUnverifiedA tester ran a 20.7B dense model on a dual-4090 (48 GB VRAM) workstation and achieved 27.6 tokens per second, only slightly faster than Dwarf Star, but with over 10 times fewer parameters.71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1030798API
curl https://kongchang.com/api/v1/knowledge/claims/1030798MCP
get_claim(id=1030798)