🔌
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 Pythia-2.8b?
Yes — here's how fast and up to what context, with real measured numbers.
Pythia-2.8b on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2587k | 1042.9-1242.9 t/s | ~5.2-6.2 (slow) |
| Q8 | yes | 2630k | 2085.7-2485.7 t/s | ~10.4-12.4 (slow) |
| Q4 | yes | 2648k | 3724.5-4438.8 t/s | ~18.6-22.2 (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-2.8b?▶
Yes. At Q4 it generates ~3724.5-4438.8 tok/s and fits up to 2648k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~18.6-22.2 tok/s.
How much context fits?▶
At Q4, up to about 2648k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.