🔌
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 EmbeddingGemma?
Yes — here's how fast and up to what context, with real measured numbers.
EmbeddingGemma on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1765k | 3483.8-4324.7 t/s | ~37.7-46.8 (slow) |
| Q8 | yes | 1769k | 6967.5-8649.4 t/s | ~75.3-93.5 (slow) |
| Q4 | yes | 1771k | 12442-15445.3 t/s | ~134.5-167 (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 EmbeddingGemma?▶
Yes. At Q4 it generates ~12442-15445.3 tok/s and fits up to 1771k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~134.5-167 tok/s.
How much context fits?▶
At Q4, up to about 1771k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.