🔌
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 Typhoon 2 1B?
Yes — here's how fast and up to what context, with real measured numbers.
LLama 3..2 Typhoon 2 1B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1743k | 1073-1332 t/s | ~11.6-14.4 (slow) |
| Q8 | yes | 1759k | 2146-2664 t/s | ~23.2-28.8 (slow) |
| Q4 | yes | 1765k | 3832.1-4757.1 t/s | ~41.4-51.4 (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 Typhoon 2 1B?▶
Yes. At Q4 it generates ~3832.1-4757.1 tok/s and fits up to 1765k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~41.4-51.4 tok/s.
How much context fits?▶
At Q4, up to about 1765k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.