🔌
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 NVIDIA GeForce RTX 3080 10GB run Adaptive Inputs + LayerDrop?
Yes — here's how fast and up to what context, with real measured numbers.
Adaptive Inputs + LayerDrop on the NVIDIA GeForce RTX 3080 10GB
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 105k | 655.8-781.6 t/s | ~34.5-41.1 (slow) |
| Q8 | yes | 111k | 1311.6-1563.1 t/s | ~69-82.3 (slow) |
| Q4 | yes | 114k | 2342.1-2791.3 t/s | ~123.3-146.9 (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.
→ All models on the NVIDIA GeForce RTX 3080 10GB
→ Adaptive Inputs + LayerDrop specs
→ Other hardware
FAQ
Can the NVIDIA GeForce RTX 3080 10GB run Adaptive Inputs + LayerDrop?▶
Yes. At Q4 it generates ~2342.1-2791.3 tok/s and fits up to 114k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~123.3-146.9 tok/s.
How much context fits?▶
At Q4, up to about 114k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.