🔌
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 MiniCPM-1.2B?
Yes — here's how fast and up to what context, with real measured numbers.
MiniCPM-1.2B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1736k | 860.2-1067.8 t/s | ~9.3-11.5 (slow) |
| Q8 | yes | 1755k | 1720.3-2135.6 t/s | ~18.6-23.1 (slow) |
| Q4 | yes | 1763k | 3072-3813.5 t/s | ~33.2-41.2 (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 MiniCPM-1.2B?▶
Yes. At Q4 it generates ~3072-3813.5 tok/s and fits up to 1763k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~33.2-41.2 tok/s.
How much context fits?▶
At Q4, up to about 1763k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.