🔌
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 Ankh_base?
Yes — here's how fast and up to what context, with real measured numbers.
Ankh_base on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1751k | 1450-1800 t/s | ~15.7-19.5 (slow) |
| Q8 | yes | 1763k | 2900-3600 t/s | ~31.4-38.9 (slow) |
| Q4 | yes | 1768k | 5178.6-6428.6 t/s | ~56-69.5 (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 Ankh_base?▶
Yes. At Q4 it generates ~5178.6-6428.6 tok/s and fits up to 1768k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~56-69.5 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.