🔌
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 WizardCoder-15.5B?
Yes — here's how fast and up to what context, with real measured numbers.
WizardCoder-15.5B on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 550k | 188.4-224.5 t/s | ~0.9-1.1 (slow) |
| Q8 | yes | 609k | 376.8-449 t/s | ~1.9-2.2 (slow) |
| Q4 | yes | 635k | 672.8-801.8 t/s | ~3.4-4 (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 WizardCoder-15.5B?▶
Yes. At Q4 it generates ~672.8-801.8 tok/s and fits up to 635k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.4-4 tok/s.
How much context fits?▶
At Q4, up to about 635k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.