New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Intel Gaudi 3 run ESM1-43M?
Yes — here's how fast and up to what context, with real measured numbers.
ESM1-43M on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1773k | 25187.8-31267.6 t/s | ~272.3-338 (slow) |
| Q8 | yes | 1773k | 50375.6-62535.2 t/s | ~544.6-676.1 (slow) |
| Q4 | yes | 1774k | 89956.4-111670 t/s | ~972.5-1207.2 (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 ESM1-43M?▶
Yes. At Q4 it generates ~89956.4-111670 tok/s and fits up to 1774k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~972.5-1207.2 tok/s.
How much context fits?▶
At Q4, up to about 1774k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.