🔌
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-Neo-2.7B?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-Neo-2.7B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1692k | 397.4-493.3 t/s | ~4.3-5.3 (slow) |
| Q8 | yes | 1733k | 794.8-986.7 t/s | ~8.6-10.7 (slow) |
| Q4 | yes | 1751k | 1419.3-1761.9 t/s | ~15.3-19 (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-Neo-2.7B?▶
Yes. At Q4 it generates ~1419.3-1761.9 tok/s and fits up to 1751k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~15.3-19 tok/s.
How much context fits?▶
At Q4, up to about 1751k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.