🔌
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 Flan T5-XXL + BLIP-2?
Yes — here's how fast and up to what context, with real measured numbers.
Flan T5-XXL + BLIP-2 on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 562k | 88.7-110.1 t/s | ~1-1.2 (slow) |
| Q8 | yes | 636k | 177.4-220.2 t/s | ~1.9-2.4 (slow) |
| Q4 | yes | 668k | 316.7-393.2 t/s | ~3.4-4.3 (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 Flan T5-XXL + BLIP-2?▶
Yes. At Q4 it generates ~316.7-393.2 tok/s and fits up to 668k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.4-4.3 tok/s.
How much context fits?▶
At Q4, up to about 668k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.