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 Pythia-160m?
Yes — here's how fast and up to what context, with real measured numbers.
Pythia-160m on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1769k | 6706.3-8325 t/s | ~72.5-90 (slow) |
| Q8 | yes | 1772k | 13412.5-16650 t/s | ~145-180 (slow) |
| Q4 | yes | 1773k | 23950.9-29732.1 t/s | ~258.9-321.4 (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 Pythia-160m?▶
Yes. At Q4 it generates ~23950.9-29732.1 tok/s and fits up to 1773k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~258.9-321.4 tok/s.
How much context fits?▶
At Q4, up to about 1773k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.