🔌
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 Transformer-XL (257M)?
Yes — here's how fast and up to what context, with real measured numbers.
Transformer-XL (257M) on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 643k | 1896.9-2305.4 t/s | ~50.6-61.5 (slow) |
| Q8 | yes | 647k | 3793.8-4610.9 t/s | ~101.2-123 (slow) |
| Q4 | yes | 649k | 6774.6-8233.7 t/s | ~180.7-219.6 (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 Transformer-XL (257M)?▶
Yes. At Q4 it generates ~6774.6-8233.7 tok/s and fits up to 649k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~180.7-219.6 tok/s.
How much context fits?▶
At Q4, up to about 649k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.