🔌
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 Qwen-Audio-Chat?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen-Audio-Chat on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 196k | 57.6-70 t/s | ~1.5-1.9 (slow) |
| Q8 | yes | 261k | 115.2-140.1 t/s | ~3.1-3.7 (slow) |
| Q4 | yes | 289k | 205.8-250.1 t/s | ~5.5-6.7 (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 Qwen-Audio-Chat?▶
Yes. At Q4 it generates ~205.8-250.1 tok/s and fits up to 289k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~5.5-6.7 tok/s.
How much context fits?▶
At Q4, up to about 289k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.