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 OpenELM-450M?
Yes — here's how fast and up to what context, with real measured numbers.
OpenELM-450M on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1760k | 2384.4-2960 t/s | ~25.8-32 (slow) |
| Q8 | yes | 1767k | 4768.9-5920 t/s | ~51.6-64 (slow) |
| Q4 | yes | 1770k | 8515.9-10571.4 t/s | ~92.1-114.3 (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 OpenELM-450M?▶
Yes. At Q4 it generates ~8515.9-10571.4 tok/s and fits up to 1770k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~92.1-114.3 tok/s.
How much context fits?▶
At Q4, up to about 1770k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.