New: connect Claude & other AIs to GenAIList over MCP — research the catalog and contribute to the shared knowledge base. Learn how →
Can the FuriosaAI RNGD run AWD-LSTM-DOC (fin) (23M)?
Yes — here's how fast and up to what context, with real measured numbers.
AWD-LSTM-DOC (fin) (23M) on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 650k | 21195.7-25760.9 t/s | ~565.2-687 (slow) |
| Q8 | yes | 651k | 42391.3-51521.7 t/s | ~1130.4-1373.9 (slow) |
| Q4 | yes | 651k | 75698.8-92003.1 t/s | ~2018.6-2453.4 (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 AWD-LSTM-DOC (fin) (23M)?▶
Yes. At Q4 it generates ~75698.8-92003.1 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~2018.6-2453.4 tok/s.
How much context fits?▶
At Q4, up to about 651k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.