🔌
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 3.2 2B?
Yes — here's how fast and up to what context, with real measured numbers.
Granite 3.2 2B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1697k | 424.1-526.5 t/s | ~4.6-5.7 (slow) |
| Q8 | yes | 1735k | 848.2-1053 t/s | ~9.2-11.4 (slow) |
| Q4 | yes | 1752k | 1514.7-1880.3 t/s | ~16.4-20.3 (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 Granite 3.2 2B?▶
Yes. At Q4 it generates ~1514.7-1880.3 tok/s and fits up to 1752k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~16.4-20.3 tok/s.
How much context fits?▶
At Q4, up to about 1752k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.