Home / Servers / 8× NVIDIA B200 192 GB
Canonical hardware · not a commercial offer
8× NVIDIA B200 192 GB
3072 GB system RAM · EPYC 9575F
Hardware
- GPU
- NVIDIA B200 192 GB
- GPU count
- 8
- VRAM per GPU
- 192 GB advertised
- Aggregate VRAM
- 1536.0 GB advertised
- System RAM
- 3072 GB
- CPU
- EPYC 9575F
- Storage
- 8 × 3576 GB NVME
- Network
- 15360 public
AI memory capability
Default catalog below is Q4 at 8K. Statuses reuse Phase 2 (1 GPU) or Phase 8 (2–4 identical GPUs). GPU counts above 4 are not modeled. Public wording is memory-capable, not serving throughput.
Memory-capable at Q4/8K: 0 published models
Serving performance
Measured vLLM serving results for this GPU identity (8× NVIDIA B200 192 GB), not a specific rental host. Tensor parallel size is stored explicitly and is not assumed equal to GPU count. Request rate is separate from concurrency; this corpus is closed-loop / max-concurrency.
| Model in source | Shape | Conc. | TP | P50 TTFT | P99 TTFT | P50 TPOT | P99 TPOT | Output tok/s |
|---|---|---|---|---|---|---|---|---|
| nvidia/Qwen3.5-397B-A17B-NVFP4 | 8192/1024 | 128 | 8 | 1.30 s | 11.47 s | 21.0 ms | 21.6 ms | 5635 tok/s |
Current rental offers
| Provider | Location | Price | Stock | |
|---|---|---|---|---|
| Vultr | — | $45696/month · $0 setup | Not listed as available | Provider |
Want to own the hardware? Build a PC · Prefer a prebuilt? Workstations