🔌
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 Gemma 2 2B?
Yes — here's how fast and up to what context, with real measured numbers.
Gemma 2 2B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1695k | 412.7-512.3 t/s | ~4.5-5.5 (slow) |
| Q8 | yes | 1734k | 825.4-1024.6 t/s | ~8.9-11.1 (slow) |
| Q4 | yes | 1752k | 1473.9-1829.7 t/s | ~15.9-19.8 (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 Gemma 2 2B?▶
Yes. At Q4 it generates ~1473.9-1829.7 tok/s and fits up to 1752k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~15.9-19.8 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.