🔌
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 XVERSE-MoE-A4.2B?
Yes — here's how fast and up to what context, with real measured numbers.
XVERSE-MoE-A4.2B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 523k | 116.1-141.1 t/s | ~3.1-3.8 (slow) |
| Q8 | yes | 587k | 232.1-282.1 t/s | ~6.2-7.5 (slow) |
| Q4 | yes | 615k | 414.5-503.8 t/s | ~11.1-13.4 (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 XVERSE-MoE-A4.2B?▶
Yes. At Q4 it generates ~414.5-503.8 tok/s and fits up to 615k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~11.1-13.4 tok/s.
How much context fits?▶
At Q4, up to about 615k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.