RTX 3060 x2 vs RTX 5090
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 509023 verified runs · best 446.7 tok/s
Specs and evidence
| RTX 3060 x2 | RTX 5090 | |
|---|---|---|
| VRAM | 12 GB | 32 GB |
| Sourced runs on the board | 29 | 23 |
| Models measured | 29 | 16 |
| Best output tok/s | 198.1 tok/s | 446.7 tok/s |
| Highest measured peak VRAM | 21.7 GB | 31.3 GB |
| Street price (latest snapshot) | — | — |
Head-to-head
On the 2 models measured on both cards, RTX 3060 x2 leads on 0, RTX 5090 on 2. The widest gap is on Qwen3.6-27B: RTX 3060 x2 18.9 tok/s vs RTX 5090 120.9 tok/s (RTX 5090 540% faster).
The measured matrix
| Model | RTX 3060 x2 | RTX 5090 |
|---|---|---|
| NVIDIA-Nemotron-3.5-Lightning-30B-A3B | — | 446.7 |
| Qwen3.8-27B | — | 435.1 |
| Ornith-1.0-35B-PrismaAURA-4.75bit-vllm-MTP | — | 283.1 |
| Kimi-Linear-48B-A3B-Instruct | — | 280.8 |
| Ornith-1.5-35B-A3B | — | 258.8 |
| North-Mini-Code-1.0 | — | 258.4 |
| Qwen3.6-35B-A3B-MTP | — | 222.9 |
| Laguna-XS-2.1 | — | 216.7 |
| KAT-Coder-V2.5-Dev-AWQ-W4A16-ASYM | — | 201.2 |
| Qwen3-1.7B | 198.1 | — |
| Ornith-1.0-35B | — | 196.6 |
| MiniCPM5-1B | 125.9 | — |
| Muse-Glimmer-30B | 56.0 | 124.8 |
| Qwen3.6-27B | 18.9 | 120.9 |
| Huihui-Qwen3.8-27B-abliterated | — | 117.7 |
| 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 | — |
| Qwen3.8-27B-5090-goldilocks | — | 93.5 |
| gpt-oss-20b | 93.4 | — |
| OpenReasoning-Nemotron-7B | 68.0 | — |
| WebWorld-8B | 62.3 | — |
| gemma-4-26B-A4B-it | 62.1 | — |
| Carnice-9b | 56.1 | — |
| 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 | — |
| Qwen3.6-27B-MTP | — | 28.3 |
| DeepSeek-V4-Flash-0731 | — | 26.4 |
| DeepHermes-3-Mistral-24B-Preview | 24.5 | — |
| reka-flash-3 | 23.9 | — |
| mistralai_Mistral-Small-3.2-24B-Instruct-2506 | 21.8 | — |
| Tess-4-27B | 18.8 | — |