🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the NVIDIA B200 run Phi-3.5-MoE?
Yes — here's how fast and up to what context, with real measured numbers.
Phi-3.5-MoE on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 163k | 48-57.2 t/s | ~0.2-0.3 (slow) |
| Q8 | yes | 349k | 96.1-114.5 t/s | ~0.5-0.6 (slow) |
| Q4 | yes | 431k | 171.5-204.4 t/s | ~0.9-1 (slow) |
Estimate (memory-bound). Beyond "max context" the KV cache spills to system RAM offload (depends on your system RAM) and speed drops to the "beyond" figure.
FAQ
Can the NVIDIA B200 run Phi-3.5-MoE?▶
Yes. At Q4 it generates ~171.5-204.4 tok/s and fits up to 431k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~0.9-1 tok/s.
How much context fits?▶
At Q4, up to about 431k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.