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-410m?
Yes — here's how fast and up to what context, with real measured numbers.
Pythia-410m on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1761k | 2617.1-3248.8 t/s | ~28.3-35.1 (slow) |
| Q8 | yes | 1768k | 5234.1-6497.6 t/s | ~56.6-70.2 (slow) |
| Q4 | yes | 1770k | 9346.7-11602.8 t/s | ~101-125.4 (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-410m?▶
Yes. At Q4 it generates ~9346.7-11602.8 tok/s and fits up to 1770k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~101-125.4 tok/s.
How much context fits?▶
At Q4, up to about 1770k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.