🔌
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 Vision 3.2 2B?
Yes — here's how fast and up to what context, with real measured numbers.
Granite Vision 3.2 2B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1683k | 360.1-447 t/s | ~3.9-4.8 (slow) |
| Q8 | yes | 1729k | 720.1-894 t/s | ~7.8-9.7 (slow) |
| Q4 | yes | 1749k | 1286-1596.4 t/s | ~13.9-17.3 (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 Vision 3.2 2B?▶
Yes. At Q4 it generates ~1286-1596.4 tok/s and fits up to 1749k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~13.9-17.3 tok/s.
How much context fits?▶
At Q4, up to about 1749k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.