🔌
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 Tranception?
Yes — here's how fast and up to what context, with real measured numbers.
Tranception on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 630k | 696.4-846.4 t/s | ~18.6-22.6 (slow) |
| Q8 | yes | 640k | 1392.9-1692.9 t/s | ~37.1-45.1 (slow) |
| Q4 | yes | 645k | 2487.2-3023 t/s | ~66.3-80.6 (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 Tranception?▶
Yes. At Q4 it generates ~2487.2-3023 tok/s and fits up to 645k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~66.3-80.6 tok/s.
How much context fits?▶
At Q4, up to about 645k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.