🔌
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 H200 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 H200
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1902k | 984.3-1173 t/s | ~8.2-9.8 (slow) |
| Q8 | yes | 1929k | 1968.5-2346.1 t/s | ~16.4-19.6 (slow) |
| Q4 | yes | 1941k | 3515.2-4189.4 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 H200 run DeepSeek-R1-Distill-Qwen-1.5B?▶
Yes. At Q4 it generates ~3515.2-4189.4 tok/s and fits up to 1941k 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 1941k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.