🔌
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 GPT-2 (774M)?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-2 (774M) on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1750k | 1386.3-1720.9 t/s | ~15-18.6 (slow) |
| Q8 | yes | 1762k | 2772.6-3441.9 t/s | ~30-37.2 (slow) |
| Q4 | yes | 1767k | 4951.1-6146.2 t/s | ~53.5-66.4 (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 GPT-2 (774M)?▶
Yes. At Q4 it generates ~4951.1-6146.2 tok/s and fits up to 1767k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~53.5-66.4 tok/s.
How much context fits?▶
At Q4, up to about 1767k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.