🔌
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 DEQ-Transformer (Medium, Adaptive Embedding)?
Yes — here's how fast and up to what context, with real measured numbers.
DEQ-Transformer (Medium, Adaptive Embedding) on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 648k | 4431.8-5386.4 t/s | ~118.2-143.6 (slow) |
| Q8 | yes | 649k | 8863.6-10772.7 t/s | ~236.4-287.3 (slow) |
| Q4 | yes | 650k | 15827.9-19237 t/s | ~422.1-513 (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.
→ All models on the FuriosaAI RNGD
→ DEQ-Transformer (Medium, Adaptive Embedding) specs
→ Other hardware
FAQ
Can the FuriosaAI RNGD run DEQ-Transformer (Medium, Adaptive Embedding)?▶
Yes. At Q4 it generates ~15827.9-19237 tok/s and fits up to 650k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~422.1-513 tok/s.
How much context fits?▶
At Q4, up to about 650k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.