🔌
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 Intel Gaudi 3 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 Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1720k | 602.8-748.3 t/s | ~6.5-8.1 (slow) |
| Q8 | yes | 1747k | 1205.6-1496.6 t/s | ~13-16.2 (slow) |
| Q4 | yes | 1759k | 2152.9-2672.6 t/s | ~23.3-28.9 (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 Intel Gaudi 3 run DeepSeek-R1-Distill-Qwen-1.5B?▶
Yes. At Q4 it generates ~2152.9-2672.6 tok/s and fits up to 1759k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~23.3-28.9 tok/s.
How much context fits?▶
At Q4, up to about 1759k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.