🔌
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 Mamba-2.8B?
Yes — here's how fast and up to what context, with real measured numbers.
Mamba-2.8B on the FuriosaAI RNGD
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 565k | 174.1-211.6 t/s | ~4.6-5.6 (slow) |
| Q8 | yes | 608k | 348.2-423.2 t/s | ~9.3-11.3 (slow) |
| Q4 | yes | 627k | 621.8-755.7 t/s | ~16.6-20.2 (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 Mamba-2.8B?▶
Yes. At Q4 it generates ~621.8-755.7 tok/s and fits up to 627k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~16.6-20.2 tok/s.
How much context fits?▶
At Q4, up to about 627k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.