🔌
New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
// RUN — FITS
Can the Intel Gaudi 3 run ProtGPT2?
Yes — here's how fast and up to what context, with real measured numbers.
ProtGPT2 on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1751k | 1453.9-1804.9 t/s | ~15.7-19.5 (slow) |
| Q8 | yes | 1763k | 2907.9-3609.8 t/s | ~31.4-39 (slow) |
| Q4 | yes | 1768k | 5192.6-6446 t/s | ~56.1-69.7 (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 ProtGPT2?▶
Yes. At Q4 it generates ~5192.6-6446 tok/s and fits up to 1768k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~56.1-69.7 tok/s.
How much context fits?▶
At Q4, up to about 1768k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.