Unverified50% confidenceBenchmarkExact time
On the 2.8-trillion-parameter KimiK3, the per-megawatt throughput of GB300-NVL72 is about 80 times that of H200, while pushing interactivity to about 215 tokens/second/user.
1
Sources
50%
Confidence
Short-term (~14 days)
Relevance
10/14/2026
First Seen
Valid until: 10/28/2026
Sources
Related Entities
Related Claims
VerifiedThe KV Cache of a 70B-parameter model with 128K context support can require hundreds of gigabytes of VRAM at full load, exceeding the 80GB VRAM capacity of a single H100.73% similarVerifiedTaking LLaMA-2 70B as an example, when processing a 4096-token context with a batch size of 32, the KV Cache can consume over 80 GB of memory.73% similarUnverifiedFor 1 million tokens, the KV Cache alone can consume hundreds of GB of VRAM at FP16 precision, far exceeding the 80 GB capacity limit of a single A100/H100.72% similarUnverifiedA developer ran the 2.8 trillion-parameter Kimi K3 model on a single MacBook Pro at approximately 1 token/second.71% similarUnverifiedLLaMA-3 70B权重约140GB，推理时每生成一个Token都需要完整遍历一次权重71% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1030799API
curl https://kongchang.com/api/v1/knowledge/claims/1030799MCP
get_claim(id=1030799)