🔌
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 LUXIA-21.4B-Alignment?
Yes — here's how fast and up to what context, with real measured numbers.
LUXIA-21.4B-Alignment on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 280k | 50.1-62.2 t/s | ~0.5-0.7 (slow) |
| Q8 | yes | 362k | 100.3-124.5 t/s | ~1.1-1.3 (slow) |
| Q4 | yes | 398k | 179.1-222.3 t/s | ~1.9-2.4 (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 LUXIA-21.4B-Alignment?▶
Yes. At Q4 it generates ~179.1-222.3 tok/s and fits up to 398k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.9-2.4 tok/s.
How much context fits?▶
At Q4, up to about 398k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.