🔌
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 Llama 3.2 3B?
Yes — here's how fast and up to what context, with real measured numbers.
Llama 3.2 3B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1676k | 334.3-415 t/s | ~3.6-4.5 (slow) |
| Q8 | yes | 1725k | 668.5-829.9 t/s | ~7.2-9 (slow) |
| Q4 | yes | 1747k | 1193.8-1482 t/s | ~12.9-16 (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 Llama 3.2 3B?▶
Yes. At Q4 it generates ~1193.8-1482 tok/s and fits up to 1747k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~12.9-16 tok/s.
How much context fits?▶
At Q4, up to about 1747k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.