🔌
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 5070 run RMBG v2.0?
Yes — here's how fast and up to what context, with real measured numbers.
RMBG v2.0 on the NVIDIA GeForce RTX 5070
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 139k | 1109.9-1322.7 t/s | ~66.1-78.7 (slow) |
| Q8 | yes | 142k | 2219.7-2645.4 t/s | ~132.1-157.5 (slow) |
| Q4 | yes | 144k | 3963.8-4724 t/s | ~235.9-281.2 (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 NVIDIA GeForce RTX 5070 run RMBG v2.0?▶
Yes. At Q4 it generates ~3963.8-4724 tok/s and fits up to 144k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~235.9-281.2 tok/s.
How much context fits?▶
At Q4, up to about 144k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.