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 ERNIE-Doc (247M)?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE-Doc (247M) on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1766k | 4344.1-5392.7 t/s | ~47-58.3 (slow) |
| Q8 | yes | 1770k | 8688.3-10785.4 t/s | ~93.9-116.6 (slow) |
| Q4 | yes | 1772k | 15514.7-19259.7 t/s | ~167.7-208.2 (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 ERNIE-Doc (247M)?▶
Yes. At Q4 it generates ~15514.7-19259.7 tok/s and fits up to 1772k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~167.7-208.2 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.