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 Tensor-Transformer(1core)+PN (WT103)?
Yes — here's how fast and up to what context, with real measured numbers.
Tensor-Transformer(1core)+PN (WT103) on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 648k | 5715.1-6946.1 t/s | ~152.4-185.2 (slow) |
| Q8 | yes | 650k | 11430.2-13892.1 t/s | ~304.8-370.5 (slow) |
| Q4 | yes | 650k | 20411.2-24807.4 t/s | ~544.3-661.5 (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 Tensor-Transformer(1core)+PN (WT103)?▶
Yes. At Q4 it generates ~20411.2-24807.4 tok/s and fits up to 650k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~544.3-661.5 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.