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 SRU++ Large?
Yes — here's how fast and up to what context, with real measured numbers.
SRU++ Large on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1767k | 4585.5-5692.3 t/s | ~49.6-61.5 (slow) |
| Q8 | yes | 1770k | 9170.9-11384.6 t/s | ~99.1-123.1 (slow) |
| Q4 | yes | 1772k | 16376.7-20329.7 t/s | ~177-219.8 (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 SRU++ Large?▶
Yes. At Q4 it generates ~16376.7-20329.7 tok/s and fits up to 1772k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~177-219.8 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.