🔌
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 11B?
Yes — here's how fast and up to what context, with real measured numbers.
Llama 3.2 11B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 580k | 101.2-125.7 t/s | ~1.1-1.4 (slow) |
| Q8 | yes | 645k | 202.5-251.3 t/s | ~2.2-2.7 (slow) |
| Q4 | yes | 673k | 361.5-448.8 t/s | ~3.9-4.9 (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 11B?▶
Yes. At Q4 it generates ~361.5-448.8 tok/s and fits up to 673k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.9-4.9 tok/s.
How much context fits?▶
At Q4, up to about 673k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.