RTX 3060 x2 vs RTX 5070 12GB + RTX 5060 Ti 16GB x2
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.
RTX 3060 x229 sourced runs · best 198.1 tok/s
RTX 5070 12GB + RTX 5060 Ti 16GB x21 verified run · best 66.0 tok/s
Specs and evidence
| RTX 3060 x2 | RTX 5070 12GB + RTX 5060 Ti 16GB x2 | |
|---|---|---|
| VRAM | 12 GB | 12 GB |
| Sourced runs on the board | 29 | 1 |
| Models measured | 29 | 1 |
| Best output tok/s | 198.1 tok/s | 66.0 tok/s |
| Highest measured peak VRAM | 21.7 GB | — |
| Street price (latest snapshot) | — | — |
The measured matrix
| Model | RTX 3060 x2 | RTX 5070 12GB + RTX 5060 Ti 16GB x2 |
|---|---|---|
| Qwen3-1.7B | 198.1 | — |
| MiniCPM5-1B | 125.9 | — |
| Trinity-Mini | 109.0 | — |
| Phi-4-mini-reasoning | 108.2 | — |
| gemma-4-26B-A4B-it-qat | 95.3 | — |
| Qwen3-30B-A3B-Thinking-2507 | 94.3 | — |
| gpt-oss-20b | 93.4 | — |
| OpenReasoning-Nemotron-7B | 68.0 | — |
| Qwen3.8-Flash-Next | — | 66.0 |
| WebWorld-8B | 62.3 | — |
| gemma-4-26B-A4B-it | 62.1 | — |
| Carnice-9b | 56.1 | — |
| Muse-Glimmer-30B | 56.0 | — |
| NVIDIA-Nemotron-Nano-12B-v2 | 40.4 | — |
| gemma-3-12b-it | 39.4 | — |
| Qwen3-14B | 35.8 | — |
| Nemotron-Cascade-14B-Thinking | 35.7 | — |
| Phi-4-reasoning | 35.4 | — |
| WebWorld-14B | 35.4 | — |
| InternVL3-14B | 35.1 | — |
| DeepSeek-R1-Distill-Qwen-14B | 35.1 | — |
| phi-4 | 34.2 | — |
| DeepHermes-3-Mistral-24B-Preview | 24.5 | — |
| reka-flash-3 | 23.9 | — |
| mistralai_Mistral-Small-3.2-24B-Instruct-2506 | 21.8 | — |
| Qwen3.6-27B | 18.9 | — |
| Tess-4-27B | 18.8 | — |
| GLM-Z1-32B-0414 | 16.6 | — |
| Olmo-3-32B-Think | 16.4 | — |
| gemma-4-31B-it | 15.8 | — |