🔌
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-VL?
Yes — here's how fast and up to what context, with real measured numbers.
Qwen-VL on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 179k | 50.8-61.7 t/s | ~1.4-1.6 (slow) |
| Q8 | yes | 252k | 101.6-123.4 t/s | ~2.7-3.3 (slow) |
| Q4 | yes | 284k | 181.4-220.4 t/s | ~4.8-5.9 (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 Qwen-VL?▶
Yes. At Q4 it generates ~181.4-220.4 tok/s and fits up to 284k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~4.8-5.9 tok/s.
How much context fits?▶
At Q4, up to about 284k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.