🔌
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 StarCoder 2 15B?
Yes — here's how fast and up to what context, with real measured numbers.
StarCoder 2 15B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 48k | 32.5-39.5 t/s | ~0.9-1.1 (slow) |
| Q8 | yes | 106k | 65-79 t/s | ~1.7-2.1 (slow) |
| Q4 | yes | 131k | 116.1-141.1 t/s | ~3.1-3.8 (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 StarCoder 2 15B?▶
Yes. At Q4 it generates ~116.1-141.1 tok/s and fits up to 131k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~3.1-3.8 tok/s.
How much context fits?▶
At Q4, up to about 131k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.