🔌
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 ERNIE-4.5-0.3B?
Yes — here's how fast and up to what context, with real measured numbers.
ERNIE-4.5-0.3B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 640k | 1354.2-1645.8 t/s | ~36.1-43.9 (slow) |
| Q8 | yes | 645k | 2708.3-3291.7 t/s | ~72.2-87.8 (slow) |
| Q4 | yes | 648k | 4836.3-5878 t/s | ~129-156.7 (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 ERNIE-4.5-0.3B?▶
Yes. At Q4 it generates ~4836.3-5878 tok/s and fits up to 648k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~129-156.7 tok/s.
How much context fits?▶
At Q4, up to about 648k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.