🔌
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 2-70B?
Yes — here's how fast and up to what context, with real measured numbers.
Llama 2-70B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | no | — | — | — |
| Q8 | yes | 141k | 30.7-38.1 t/s | ~0.3-0.4 (slow) |
| Q4 | yes | 235k | 54.7-68 t/s | ~0.6-0.7 (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 2-70B?▶
Yes. At Q4 it generates ~54.7-68 tok/s and fits up to 235k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~0.6-0.7 tok/s.
How much context fits?▶
At Q4, up to about 235k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.