🔌
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 Pharia-1-LLM-7B?
Yes — here's how fast and up to what context, with real measured numbers.
Pharia-1-LLM-7B on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1229k | 414.7-494.2 t/s | ~2.1-2.5 (slow) |
| Q8 | yes | 1282k | 829.4-988.4 t/s | ~4.1-4.9 (slow) |
| Q4 | yes | 1306k | 1481-1765 t/s | ~7.4-8.8 (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 Pharia-1-LLM-7B?▶
Yes. At Q4 it generates ~1481-1765 tok/s and fits up to 1306k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~7.4-8.8 tok/s.
How much context fits?▶
At Q4, up to about 1306k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.