🔌
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 Nanbeige-16B?
Yes — here's how fast and up to what context, with real measured numbers.
Nanbeige-16B on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 321k | 67.1-83.3 t/s | ~0.7-0.9 (slow) |
| Q8 | yes | 382k | 134.1-166.5 t/s | ~1.5-1.8 (slow) |
| Q4 | yes | 409k | 239.5-297.3 t/s | ~2.6-3.2 (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 Nanbeige-16B?▶
Yes. At Q4 it generates ~239.5-297.3 tok/s and fits up to 409k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2.6-3.2 tok/s.
How much context fits?▶
At Q4, up to about 409k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.