🔌
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 Unicorn?
Yes — here's how fast and up to what context, with real measured numbers.
Unicorn on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 935k | 265.5-316.4 t/s | ~1.3-1.6 (slow) |
| Q8 | yes | 1002k | 530.9-632.7 t/s | ~2.7-3.2 (slow) |
| Q4 | yes | 1031k | 948.1-1129.9 t/s | ~4.7-5.6 (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 Unicorn?▶
Yes. At Q4 it generates ~948.1-1129.9 tok/s and fits up to 1031k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~4.7-5.6 tok/s.
How much context fits?▶
At Q4, up to about 1031k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.