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 CodeT5-base?
Yes — here's how fast and up to what context, with real measured numbers.
CodeT5-base on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1767k | 4877.3-6054.5 t/s | ~52.7-65.5 (slow) |
| Q8 | yes | 1771k | 9754.5-12109.1 t/s | ~105.5-130.9 (slow) |
| Q4 | yes | 1772k | 17418.8-21623.4 t/s | ~188.3-233.8 (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 CodeT5-base?▶
Yes. At Q4 it generates ~17418.8-21623.4 tok/s and fits up to 1772k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~188.3-233.8 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.