🔌
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 DeepSeek-R1-Distill-Qwen-1.5B?
Yes — here's how fast and up to what context, with real measured numbers.
DeepSeek-R1-Distill-Qwen-1.5B on the NVIDIA B200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 2618k | 1640.4-1955.1 t/s | ~8.2-9.8 (slow) |
| Q8 | yes | 2645k | 3280.9-3910.1 t/s | ~16.4-19.6 (slow) |
| Q4 | yes | 2657k | 5858.7-6982.3 t/s | ~29.3-34.9 (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 DeepSeek-R1-Distill-Qwen-1.5B?▶
Yes. At Q4 it generates ~5858.7-6982.3 tok/s and fits up to 2657k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~29.3-34.9 tok/s.
How much context fits?▶
At Q4, up to about 2657k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.