New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the NVIDIA B200 run Pythia-1b?
Yes — here's how fast and up to what context, with real measured numbers.
Pythia-1b on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2642k | 2920-3480 t/s | ~14.6-17.4 (slow) |
| Q8 | yes | 2657k | 5840-6960 t/s | ~29.2-34.8 (slow) |
| Q4 | yes | 2664k | 10428.6-12428.6 t/s | ~52.1-62.1 (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 Pythia-1b?▶
Yes. At Q4 it generates ~10428.6-12428.6 tok/s and fits up to 2664k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~52.1-62.1 tok/s.
How much context fits?▶
At Q4, up to about 2664k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.