🔌
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 gte-modernbert?
Yes — here's how fast and up to what context, with real measured numbers.
gte-modernbert on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 646k | 3271.8-3976.5 t/s | ~87.2-106 (slow) |
| Q8 | yes | 649k | 6543.6-7953 t/s | ~174.5-212.1 (slow) |
| Q4 | yes | 650k | 11685-14201.8 t/s | ~311.6-378.7 (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 gte-modernbert?▶
Yes. At Q4 it generates ~11685-14201.8 tok/s and fits up to 650k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~311.6-378.7 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.