🔌
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 DeciCoder-1B?
Yes — here's how fast and up to what context, with real measured numbers.
DeciCoder-1B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1740k | 975.5-1210.9 t/s | ~10.5-13.1 (slow) |
| Q8 | yes | 1757k | 1950.9-2421.8 t/s | ~21.1-26.2 (slow) |
| Q4 | yes | 1765k | 3483.8-4324.7 t/s | ~37.7-46.8 (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 DeciCoder-1B?▶
Yes. At Q4 it generates ~3483.8-4324.7 tok/s and fits up to 1765k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~37.7-46.8 tok/s.
How much context fits?▶
At Q4, up to about 1765k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.