RTX 2060 Super vs RTX 5070
Best sourced output tok/s per model (single-stream generation) — engine and version, quantization, context and a source link on every row. Hover a value for the quant.
Sourced data on this pair is thin — most of the board is still partial. Submit your own run and help fill the matrix: one prompt, three steps, no downloads.
RTX 2060 Super3 sourced runs · best 97.1 tok/s
RTX 50705 verified runs · best 185.8 tok/s
Specs and evidence
| RTX 2060 Super | RTX 5070 | |
|---|---|---|
| VRAM | 8 GB | 12 GB |
| Sourced runs on the board | 3 | 5 |
| Models measured | 3 | 5 |
| Best output tok/s | 97.1 tok/s | 185.8 tok/s |
| Highest measured peak VRAM | 6.7 GB | 9.0 GB |
| Street price (latest snapshot) | — | — |
Head-to-head
Only one model has been measured on both cards (Ornith-1.5-9B). On that single data point RTX 2060 Super records 60.4 tok/s and RTX 5070 records 102.0 tok/s — treat it as one data point, not a ranking.