🔌
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 3070 Ti run CLIP (ViT L/14@336px)?
Yes — here's how fast and up to what context, with real measured numbers.
CLIP (ViT L/14@336px) on the NVIDIA GeForce RTX 3070 Ti
| Quant | Fits? | Max context | Speed | Beyond context |
|---|---|---|---|---|
| FP16 | yes | 78k | 599.8-714.8 t/s | ~39.5-47 (slow) |
| Q8 | yes | 84k | 1199.6-1429.6 t/s | ~78.9-94.1 (slow) |
| Q4 | yes | 86k | 2142.1-2552.9 t/s | ~140.9-168 (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 3070 Ti run CLIP (ViT L/14@336px)?▶
Yes. At Q4 it generates ~2142.1-2552.9 tok/s and fits up to 86k context; beyond that it spills to system RAM offload (depends on your system RAM) and slows to ~140.9-168 tok/s.
How much context fits?▶
At Q4, up to about 86k tokens stay in fast memory; longer context spills to system RAM offload (depends on your system RAM) and throughput collapses.