🔌
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 FuriosaAI RNGD run LDM-1.45B?
Yes — here's how fast and up to what context, with real measured numbers.
LDM-1.45B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 607k | 336.2-408.6 t/s | ~9-10.9 (slow) |
| Q8 | yes | 629k | 672.4-817.2 t/s | ~17.9-21.8 (slow) |
| Q4 | yes | 639k | 1200.7-1459.4 t/s | ~32-38.9 (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 FuriosaAI RNGD run LDM-1.45B?▶
Yes. At Q4 it generates ~1200.7-1459.4 tok/s and fits up to 639k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~32-38.9 tok/s.
How much context fits?▶
At Q4, up to about 639k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.