🔌
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 EXAONE Deep 2.4B?
Yes — here's how fast and up to what context, with real measured numbers.
EXAONE Deep 2.4B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1701k | 447.1-555 t/s | ~4.8-6 (slow) |
| Q8 | yes | 1737k | 894.2-1110 t/s | ~9.7-12 (slow) |
| Q4 | yes | 1753k | 1596.7-1982.1 t/s | ~17.3-21.4 (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 EXAONE Deep 2.4B?▶
Yes. At Q4 it generates ~1596.7-1982.1 tok/s and fits up to 1753k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~17.3-21.4 tok/s.
How much context fits?▶
At Q4, up to about 1753k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.