🔌
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 Foundation-sec-8b?
Yes — here's how fast and up to what context, with real measured numbers.
Foundation-sec-8b on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 765k | 134.1-166.5 t/s | ~1.5-1.8 (slow) |
| Q8 | yes | 826k | 268.3-333 t/s | ~2.9-3.6 (slow) |
| Q4 | yes | 853k | 479-594.6 t/s | ~5.2-6.4 (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 Intel Gaudi 3 run Foundation-sec-8b?▶
Yes. At Q4 it generates ~479-594.6 tok/s and fits up to 853k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.2-6.4 tok/s.
How much context fits?▶
At Q4, up to about 853k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.