🔌
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-33B?
Yes — here's how fast and up to what context, with real measured numbers.
LLaMA-33B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 196k | 33-41 t/s | ~0.4-0.4 (slow) |
| Q8 | yes | 320k | 66-82 t/s | ~0.7-0.9 (slow) |
| Q4 | yes | 374k | 117.9-146.4 t/s | ~1.3-1.6 (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-33B?▶
Yes. At Q4 it generates ~117.9-146.4 tok/s and fits up to 374k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1.3-1.6 tok/s.
How much context fits?▶
At Q4, up to about 374k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.