🔌
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 ESM1v?
Yes — here's how fast and up to what context, with real measured numbers.
ESM1v on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1754k | 1650.8-2049.2 t/s | ~17.8-22.2 (slow) |
| Q8 | yes | 1764k | 3301.5-4098.5 t/s | ~35.7-44.3 (slow) |
| Q4 | yes | 1768k | 5895.6-7318.7 t/s | ~63.7-79.1 (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 ESM1v?▶
Yes. At Q4 it generates ~5895.6-7318.7 tok/s and fits up to 1768k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~63.7-79.1 tok/s.
How much context fits?▶
At Q4, up to about 1768k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.