🔌
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 data2vec (language)?
Yes — here's how fast and up to what context, with real measured numbers.
data2vec (language) on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1752k | 1521.7-1889 t/s | ~16.5-20.4 (slow) |
| Q8 | yes | 1763k | 3043.4-3778 t/s | ~32.9-40.8 (slow) |
| Q4 | yes | 1768k | 5434.6-6746.4 t/s | ~58.8-72.9 (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 data2vec (language)?▶
Yes. At Q4 it generates ~5434.6-6746.4 tok/s and fits up to 1768k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~58.8-72.9 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.