Kimi K3 Scale Exceeds Single B200 Capacity
airesearch12 · x · 2026-07-17
According to SemiAnalysis, the 2.8T parameter scale of Kimi K3 is too large to fit on a single NVIDIA DGX B200, even in FP4.
Deployment requires systems like the GB300 NVL72, B300, or MI355X, as each GPU needs 288GB of VRAM. Optimizing for the B200 might require tying multiple nodes together using WideEP; however, the B200's inter-node bandwidth is only 400 Gbit/s, whereas the NVL72 boasts an inter-node bandwidth 18 times higher.
Related event: Kimi K3 Triggers a Reassessment of Chinese Frontier AI(94 posts)→
More from Infra
- SGLang MegaKernel + PD Pushes the TCO-Latency Frontier on GB300, SemiAnalysis Benchmarks Show — AccBalanced · 2026-10-27
- Anthropic hits $16.3B H1 revenue as compute efficiency jumps 5.2x in 18 months — daniel_mac8 · 2026-10-27
- Tenstorrent runs Proteina protein model at high throughput, claims no HBM shortage — gajesh · 2026-10-27
- YC-backed Hopper launches voice-agent inference cloud: 80 ms TTFT at $0.30/1M tokens — ycombinator · 2026-10-27
- A100 rental prices still rising in 2026 per a16z data, Jevons paradox hits compute — VraserX · 2026-10-27
- Anthropic S-1 reveals $800B+ in off-books future compute commitments — GaryMarcus · 2026-10-27