🔌
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 NVIDIA-Nemotron-Nano-9B-v2?
Yes — here's how fast and up to what context, with real measured numbers.
NVIDIA-Nemotron-Nano-9B-v2 on the Intel Gaudi 3
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 750k | 119.2-148 t/s | ~1.3-1.6 (slow) |
| Q8 | yes | 818k | 238.4-296 t/s | ~2.6-3.2 (slow) |
| Q4 | yes | 849k | 425.8-528.6 t/s | ~4.6-5.7 (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 NVIDIA-Nemotron-Nano-9B-v2?▶
Yes. At Q4 it generates ~425.8-528.6 tok/s and fits up to 849k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~4.6-5.7 tok/s.
How much context fits?▶
At Q4, up to about 849k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.