🔌
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 4070 Ti Super run Depth Anything V2 Large?
Yes — here's how fast and up to what context, with real measured numbers.
Depth Anything V2 Large on the NVIDIA GeForce RTX 4070 Ti Super
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 191k | 731.5-871.8 t/s | ~43.5-51.9 (slow) |
| Q8 | yes | 197k | 1463-1743.6 t/s | ~87.1-103.8 (slow) |
| Q4 | yes | 199k | 2612.6-3113.6 t/s | ~155.5-185.3 (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 4070 Ti Super
→ Depth Anything V2 Large specs
→ Other hardware
FAQ
Can the NVIDIA GeForce RTX 4070 Ti Super run Depth Anything V2 Large?▶
Yes. At Q4 it generates ~2612.6-3113.6 tok/s and fits up to 199k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~155.5-185.3 tok/s.
How much context fits?▶
At Q4, up to about 199k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.