🔌
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 ESM3-open-small?
Yes — here's how fast and up to what context, with real measured numbers.
ESM3-open-small on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1731k | 766.4-951.4 t/s | ~8.3-10.3 (slow) |
| Q8 | yes | 1753k | 1532.9-1902.9 t/s | ~16.6-20.6 (slow) |
| Q4 | yes | 1762k | 2737.2-3398 t/s | ~29.6-36.7 (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 ESM3-open-small?▶
Yes. At Q4 it generates ~2737.2-3398 tok/s and fits up to 1762k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~29.6-36.7 tok/s.
How much context fits?▶
At Q4, up to about 1762k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.