🔌
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 Retrieval-Augmented Generator?
Yes — here's how fast and up to what context, with real measured numbers.
Retrieval-Augmented Generator on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1755k | 1714.1-2127.8 t/s | ~18.5-23 (slow) |
| Q8 | yes | 1764k | 3428.1-4255.6 t/s | ~37.1-46 (slow) |
| Q4 | yes | 1769k | 6121.6-7599.3 t/s | ~66.2-82.2 (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 Intel Gaudi 3 run Retrieval-Augmented Generator?▶
Yes. At Q4 it generates ~6121.6-7599.3 tok/s and fits up to 1769k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~66.2-82.2 tok/s.
How much context fits?▶
At Q4, up to about 1769k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.