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 MatterGen?
Yes — here's how fast and up to what context, with real measured numbers.
MatterGen on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1773k | 22927.4-28461.5 t/s | ~247.9-307.7 (slow) |
| Q8 | yes | 1773k | 45854.7-56923.1 t/s | ~495.7-615.4 (slow) |
| Q4 | yes | 1774k | 81883.4-101648.4 t/s | ~885.2-1098.9 (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 MatterGen?▶
Yes. At Q4 it generates ~81883.4-101648.4 tok/s and fits up to 1774k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~885.2-1098.9 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.