🔌
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 GLIDE?
Yes — here's how fast and up to what context, with real measured numbers.
GLIDE on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 544k | 139.3-169.3 t/s | ~3.7-4.5 (slow) |
| Q8 | yes | 598k | 278.6-338.6 t/s | ~7.4-9 (slow) |
| Q4 | yes | 621k | 497.4-604.6 t/s | ~13.3-16.1 (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 GLIDE?▶
Yes. At Q4 it generates ~497.4-604.6 tok/s and fits up to 621k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~13.3-16.1 tok/s.
How much context fits?▶
At Q4, up to about 621k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.