🔌
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 DeepSeek-R1-Distill-Qwen-1.5B?
Yes — here's how fast and up to what context, with real measured numbers.
DeepSeek-R1-Distill-Qwen-1.5B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 597k | 273.9-332.9 t/s | ~7.3-8.9 (slow) |
| Q8 | yes | 624k | 547.8-665.7 t/s | ~14.6-17.8 (slow) |
| Q4 | yes | 636k | 978.1-1188.8 t/s | ~26.1-31.7 (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 DeepSeek-R1-Distill-Qwen-1.5B?▶
Yes. At Q4 it generates ~978.1-1188.8 tok/s and fits up to 636k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~26.1-31.7 tok/s.
How much context fits?▶
At Q4, up to about 636k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.