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) (37M)?
Yes — here's how fast and up to what context, with real measured numbers.
AWD-LSTM-DOC (fin) (37M) on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 650k | 13175.7-16013.5 t/s | ~351.4-427 (slow) |
| Q8 | yes | 650k | 26351.4-32027 t/s | ~702.7-854.1 (slow) |
| Q4 | yes | 651k | 47056-57191.1 t/s | ~1254.8-1525.1 (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) (37M)?▶
Yes. At Q4 it generates ~47056-57191.1 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1254.8-1525.1 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.