🔌
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 Llama-Primus-Nemotron-70B?
Yes — here's how fast and up to what context, with real measured numbers.
Llama-Primus-Nemotron-70B on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 107k | 41.7-49.7 t/s | ~0.2-0.2 (slow) |
| Q8 | yes | 321k | 83.4-99.4 t/s | ~0.4-0.5 (slow) |
| Q4 | yes | 415k | 149-177.6 t/s | ~0.7-0.9 (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 Llama-Primus-Nemotron-70B?▶
Yes. At Q4 it generates ~149-177.6 tok/s and fits up to 415k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~0.7-0.9 tok/s.
How much context fits?▶
At Q4, up to about 415k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.