RTX 3060 x2 vs RTX PRO 6000 Blackwell
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 PRO 6000 Blackwell29 verified runs · best 1271.3 tok/s
Specs and evidence
| RTX 3060 x2 | RTX PRO 6000 Blackwell | |
|---|---|---|
| VRAM | 12 GB | 96 GB |
| Sourced runs on the board | 29 | 29 |
| Models measured | 29 | 23 |
| Best output tok/s | 198.1 tok/s | 1271.3 tok/s |
| Highest measured peak VRAM | 21.7 GB | 72.7 GB |
| Street price (latest snapshot) | — | — |
Head-to-head
On the 3 models measured on both cards, RTX 3060 x2 leads on 0, RTX PRO 6000 Blackwell on 3. The widest gap is on Qwen3.6-27B: RTX 3060 x2 18.9 tok/s vs RTX PRO 6000 Blackwell 101.4 tok/s (RTX PRO 6000 Blackwell 437% faster).
The measured matrix
| Model | RTX 3060 x2 | RTX PRO 6000 Blackwell |
|---|---|---|
| MobileLLM-125M | — | 1271.3 |
| Qwen2.5-0.5B-Instruct | — | 1060.0 |
| MobileLLM-350M | — | 980.8 |
| SmolLM2-360M-Instruct | — | 968.1 |
| Qwen3-0.6B | — | 956.4 |
| Llama-3.2-1B-Instruct | — | 699.9 |
| gemma-3-1b-it | — | 664.3 |
| Llama-3.2-3B-Instruct | — | 489.2 |
| Ling-3.0-tiny | — | 369.1 |
| Qwen3.6-35B-A3B | — | 330.2 |
| Ornith-1.0-35B | — | 309.7 |
| Qwen3.8-27B | — | 296.0 |
| DeepSeek-Coder-V2-Lite-Instruct | — | 237.3 |
| Qwen3-1.7B | 198.1 | — |
| Qwen3-Coder-Next | — | 174.3 |
| Llama-3.1-8B-Instruct | — | 158.1 |
| Muse-Glimmer-30B | 56.0 | 152.2 |
| MiniCPM5-1B | 125.9 | — |
| Qwen3.8-27B-MTP | — | 112.1 |
| Trinity-Mini | 109.0 | — |
| Phi-4-mini-reasoning | 108.2 | — |
| Qwen3.6-27B | 18.9 | 101.4 |
| gemma-4-26B-A4B-it-qat | 95.3 | — |
| Qwen3-30B-A3B-Thinking-2507 | 94.3 | — |
| gpt-oss-20b | 93.4 | — |
| Qwen3-14B | 35.8 | 90.8 |
| Kimi-Linear-48B-A3B-Instruct | — | 90.0 |
| OpenReasoning-Nemotron-7B | 68.0 | — |
| WebWorld-8B | 62.3 | — |
| gemma-4-26B-A4B-it | 62.1 | — |
| Qwen3.6-27B-MTP | — | 60.1 |
| Carnice-9b | 56.1 | — |
| Qwen2.5-Coder-14B-Instruct | — | 50.3 |
| NVIDIA-Nemotron-Nano-12B-v2 | 40.4 | — |
| gemma-3-12b-it | 39.4 | — |
| 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 | — |