🔌
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 Instinct MI440X run Nemotron-H 47B?
Yes — here's how fast and up to what context, with real measured numbers.
Nemotron-H 47B on the Instinct MI440X
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 921k | 131.4-160.6 t/s | ~0.3-0.3 (slow) |
| Q8 | yes | 1065k | 262.7-321.1 t/s | ~0.5-0.7 (slow) |
| Q4 | yes | 1128k | 469.1-573.4 t/s | ~1-1.2 (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 Instinct MI440X run Nemotron-H 47B?▶
Yes. At Q4 it generates ~469.1-573.4 tok/s and fits up to 1128k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1-1.2 tok/s.
How much context fits?▶
At Q4, up to about 1128k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.