Blackwell B300 sustains 6x concurrent agents vs H200 in tests
ryanshrout · x · 2026-09-02
Signal65 PINNACLE benchmarks show NVIDIA Blackwell Ultra B300 supports 6x more concurrent agents than H200 on a fully loaded 8-GPU node (96 vs 16) under agentic workloads with 90K tokens context per agent. Across seven models, B300 showed a 3.15x average increase. A single B300 node sustained a 320-agent workforce on Qwen3.5-35B-A3B.
Related event: B300 Sustains 6x More Concurrent Agents Than H200 in Benchmark(2 posts)→
More from Infra
- Auction-based LLM routing paper finds fixed token pricing wastes 10%-71% in costs — _onionesque · 2026-10-18
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- SGLang Summit sponsors jump from 11 to 36 in one week — ying11231 · 2026-10-18
- Oracle CDS hits record 300bps, called first AI trade domino after Barclays sell downgrade — arthurcolle · 2026-10-18
- Agent Coding Workflow Would Cost ~$40k/Month on API Pricing, Dev Reveals — ChrisRackauckas · 2026-10-18
- PS5LM: llama.cpp port turns a jailbroken PS5 into a home LLM server (500+ GitHub stars) — wateriscoding · 2026-10-18