🔌
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 GPT-Neo-2.7B?
Yes — here's how fast and up to what context, with real measured numbers.
GPT-Neo-2.7B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 569k | 180.6-219.4 t/s | ~4.8-5.9 (slow) |
| Q8 | yes | 610k | 361.1-438.9 t/s | ~9.6-11.7 (slow) |
| Q4 | yes | 628k | 644.8-783.7 t/s | ~17.2-20.9 (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 GPT-Neo-2.7B?▶
Yes. At Q4 it generates ~644.8-783.7 tok/s and fits up to 628k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~17.2-20.9 tok/s.
How much context fits?▶
At Q4, up to about 628k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.