🔌
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 ProGen2-base?
Yes — here's how fast and up to what context, with real measured numbers.
ProGen2-base on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1751k | 1404.5-1743.5 t/s | ~15.2-18.8 (slow) |
| Q8 | yes | 1762k | 2808.9-3486.9 t/s | ~30.4-37.7 (slow) |
| Q4 | yes | 1767k | 5015.9-6226.6 t/s | ~54.2-67.3 (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 ProGen2-base?▶
Yes. At Q4 it generates ~5015.9-6226.6 tok/s and fits up to 1767k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~54.2-67.3 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.