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 OpenPhenom-S/16?
Yes — here's how fast and up to what context, with real measured numbers.
OpenPhenom-S/16 on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1769k | 6026.5-7481.2 t/s | ~65.2-80.9 (slow) |
| Q8 | yes | 1771k | 12053.1-14962.5 t/s | ~130.3-161.8 (slow) |
| Q4 | yes | 1772k | 21523.4-26718.7 t/s | ~232.7-288.9 (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 OpenPhenom-S/16?▶
Yes. At Q4 it generates ~21523.4-26718.7 tok/s and fits up to 1772k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~232.7-288.9 tok/s.
How much context fits?▶
At Q4, up to about 1772k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.