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 TiTok-L?
Yes — here's how fast and up to what context, with real measured numbers.
TiTok-L on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1765k | 3495.1-4338.8 t/s | ~37.8-46.9 (slow) |
| Q8 | yes | 1769k | 6990.2-8677.5 t/s | ~75.6-93.8 (slow) |
| Q4 | yes | 1771k | 12482.6-15495.6 t/s | ~134.9-167.5 (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 TiTok-L?▶
Yes. At Q4 it generates ~12482.6-15495.6 tok/s and fits up to 1771k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~134.9-167.5 tok/s.
How much context fits?▶
At Q4, up to about 1771k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.