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 GemNet-T (OC20)?
Yes — here's how fast and up to what context, with real measured numbers.
GemNet-T (OC20) on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 651k | 256578.9-311842.1 t/s | ~6842.1-8315.8 (slow) |
| Q8 | yes | 651k | 513157.9-623684.2 t/s | ~13684.2-16631.6 (slow) |
| Q4 | yes | 651k | 916353.4-1113721.8 t/s | ~24436.1-29699.2 (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 GemNet-T (OC20)?▶
Yes. At Q4 it generates ~916353.4-1113721.8 tok/s and fits up to 651k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~24436.1-29699.2 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.