New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the Intel Gaudi 3 run Segatron XL base, M=384?
Yes — here's how fast and up to what context, with real measured numbers.
Segatron XL base, M=384 on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 1766k | 4175.1-5182.9 t/s | ~45.1-56 (slow) |
| Q8 | yes | 1770k | 8350.2-10365.8 t/s | ~90.3-112.1 (slow) |
| Q4 | yes | 1772k | 14911.1-18510.3 t/s | ~161.2-200.1 (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 Segatron XL base, M=384?▶
Yes. At Q4 it generates ~14911.1-18510.3 tok/s and fits up to 1772k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~161.2-200.1 tok/s.
How much context fits?▶
At Q4, up to about 1772k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.