🔌
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 Granite SWASH 3B?
Yes — here's how fast and up to what context, with real measured numbers.
Granite SWASH 3B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1682k | 355.3-441.1 t/s | ~3.8-4.8 (slow) |
| Q8 | yes | 1728k | 710.6-882.1 t/s | ~7.7-9.5 (slow) |
| Q4 | yes | 1748k | 1268.9-1575.2 t/s | ~13.7-17 (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 Granite SWASH 3B?▶
Yes. At Q4 it generates ~1268.9-1575.2 tok/s and fits up to 1748k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~13.7-17 tok/s.
How much context fits?▶
At Q4, up to about 1748k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.