🔌
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 SeaLLM-7B-v2?
Yes — here's how fast and up to what context, with real measured numbers.
SeaLLM-7B-v2 on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1224k | 395.7-471.5 t/s | ~2-2.4 (slow) |
| Q8 | yes | 1280k | 791.3-943.1 t/s | ~4-4.7 (slow) |
| Q4 | yes | 1305k | 1413.1-1684.1 t/s | ~7.1-8.4 (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 SeaLLM-7B-v2?▶
Yes. At Q4 it generates ~1413.1-1684.1 tok/s and fits up to 1305k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~7.1-8.4 tok/s.
How much context fits?▶
At Q4, up to about 1305k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.