New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Intel Gaudi 3 run OPT-350M?
Yes — here's how fast and up to what context, with real measured numbers.
OPT-350M on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1763k | 3065.7-3805.7 t/s | ~33.1-41.1 (slow) |
| Q8 | yes | 1769k | 6131.4-7611.4 t/s | ~66.3-82.3 (slow) |
| Q4 | yes | 1771k | 10949-13591.8 t/s | ~118.4-146.9 (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 OPT-350M?▶
Yes. At Q4 it generates ~10949-13591.8 tok/s and fits up to 1771k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~118.4-146.9 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.