🔌
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 Jamba?
Yes — here's how fast and up to what context, with real measured numbers.
Jamba on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 220k | 56.6-67.4 t/s | ~0.3-0.3 (slow) |
| Q8 | yes | 377k | 113.2-134.9 t/s | ~0.6-0.7 (slow) |
| Q4 | yes | 446k | 202.1-240.9 t/s | ~1-1.2 (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 Jamba?▶
Yes. At Q4 it generates ~202.1-240.9 tok/s and fits up to 446k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1-1.2 tok/s.
How much context fits?▶
At Q4, up to about 446k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.