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 TrellisNet-MoS (1.4x larger) PTB?
Yes — here's how fast and up to what context, with real measured numbers.
TrellisNet-MoS (1.4x larger) PTB on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 650k | 14338.2-17426.5 t/s | ~382.4-464.7 (slow) |
| Q8 | yes | 650k | 28676.5-34852.9 t/s | ~764.7-929.4 (slow) |
| Q4 | yes | 651k | 51208-62237.4 t/s | ~1365.5-1659.7 (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 TrellisNet-MoS (1.4x larger) PTB?▶
Yes. At Q4 it generates ~51208-62237.4 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~1365.5-1659.7 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.