12GB · AI Score 2.6/100 · first-party measured on 12 AI workloads
2.6 AI Score Includes estimates
Every number on this page is first-party: NVIDIA GeForce RTX 3060 was run on our pinned 12-workload AI suite on 2026-07-11, with under 0.5% run-to-run variance. On Llama 3.1 8B (Q4_K_M) NVIDIA GeForce RTX 3060 delivers about 65.36 tokens/sec. Llama 3.3 70B does not fit. It needs roughly 42GB and this card has 12GB. For image generation, SDXL runs at 1.47 it/s, while FLUX.1-dev won't fit at BF16 (needs ~26GB). 8 of the 12 workloads won't fit on 12GB at the tested precision, Qwen3 32B, Llama 3.3 70B, Z-Image Turbo, FLUX.1-dev and others. We publish those as hard gates rather than quietly dropping to a smaller quant.
The 12GB on a budget card is the whole reason to look at this, it loads things the 8GB cards can't. It also ran 6% over its official power rating, which tells you Ampere ratings were optimistic. Slow, but honest about what fits. Quick note on the setup: all my AI benchmarking was done on rented cloud GPUs, I used all three of Vast.ai, RunPod and Modal depending on which had the card, and they all have their pros and cons. Same pinned harness on every run, and everything here got double-checked before it went up.
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Qwen3 0.6B | 345.2 tok/s | 71 W72°CQ4_K_M | ✓ Measured |
| Llama 3.2 1B | 303.7 tok/s | 91 W71°CQ4_K_M | ✓ Measured |
| MiniCPM5 2B | 167.64 tok/s | 105 W61°CQ4_K_M | ✓ Measured |
| LFM2.5 2.6B | 154.94 tok/s | 116 W68°CQ4_K_M | ✓ Measured |
| Agents-A1-4B | 89.57 tok/s | 130 W58°CQ4_K_M | ✓ Measured |
| Nemotron 3 Nano 4B | 100.43 tok/s | 118 W64°CQ4_K_M | ✓ Measured |
| Qwen3 4B | 102.04 tok/s | 2.8 GB peak128 W63°C0.8 tok/WQ4_K_M | ✓ Measured |
| Spark-X2.5-4B | 98.43 tok/s | 129 W54°CQ4_K_M | ✓ Measured |
| OLMo 3 7B Instruct | 69.19 tok/s | 134 W58°CQ4_K_M | ✓ Measured |
| OLMo 3 7B Think | 69.18 tok/s | 135 W58°CQ4_K_M | ✓ Measured |
| Qwen2-7B-Instruct | 68.27 tok/s | 135 W56°CQ4_K_M | ✓ Measured |
| Qwen2.5-7B | 67.57 tok/s | 135 W73°CQ4_K_M | ✓ Measured |
| Qwen2.5-Coder 7B | 67.58 tok/s | 133 W70°CQ4_K_M | ✓ Measured |
| Apertus-8B-Instruct | 63.45 tok/s | 137 W58°CQ4_K_M | ✓ Measured |
| Llama 3.1 8B | 65.36 tok/s | 4.8 GB peak146 W67°C0.45 tok/WQ4_K_M | ✓ Measured |
| Qwen3 8B | 63.84 tok/s | 132 W64°CQ4_K_M | ✓ Measured |
| Ornith 1.5 9B | 56.51 tok/s | 133 W63°CQ4_K_M | ✓ Measured |
| Gemma 4 12B | 41.02 tok/s | 136 W66°CQ4_K_M | ✓ Measured |
| Qwen2.5-Coder 14B | 35.52 tok/s | 8.5 GB peak147 W71°C0.24 tok/WQ4_K_M | ✓ Measured |
| Qwen3 14B | 36.45 tok/s | 142 W66°CQ4_K_M | ✓ Measured |
| Gemma 4 26B A4B | ✕ Won't fit needs ~20 GB | VRAM-gated at this precision | Est. |
| Qwen3 30B A3B | ✕ Won't fit needs ~20 GB | VRAM-gated at this precision | Est. |
| Gemma 4 31B | ✕ Won't fit needs ~22 GB | VRAM-gated at this precision | Est. |
| Qwen3 32B | ✕ Won't fit needs ~23 GB | VRAM-gated at this precision | ✓ Measured |
| Llama 3.3 70B | ✕ Won't fit needs ~46 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Stable Diffusion 1.5 | 15.9 images/min | 147 W69°C | ✓ Measured |
| SD Turbo | 267.93 images/min | 61 W56°C | ✓ Measured |
| Stable Diffusion 2.1 | 17.71 images/min | 162 W69°C | ✓ Measured |
| LCM DreamShaper v7 | 62.2 images/min | 133 W57°C | ✓ Measured |
| SDXL Turbo | 216.61 images/min | 83 W58°C | ✓ Measured |
| SSD-1B | 2.72 images/min | 159 W86°C | ✓ Measured |
| Sana 1.6B | 7.4 images/min | 140 W64°C | ✓ Measured |
| Stable Diffusion XL | 2.94 images/min | 11.7 GB peak173 W73°C20.4 s/img | ✓ Measured |
| DreamShaper XL Lightning | 18.28 images/min | 147 W67°C | ✓ Measured |
| DreamShaper XL Turbo | 10.14 images/min | 154 W68°C | ✓ Measured |
| Playground v2.5 | 1.76 images/min | 152 W69°C | ✓ Measured |
| Z-Image Turbo | ✕ Won't fit needs ~13 GB | VRAM-gated at this precision | ✓ Measured |
| FLUX.1 dev | ✕ Won't fit needs ~26 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| FLUX.1 Kontext dev | ✕ Won't fit needs ~26 GB | VRAM-gated at this precision | ✓ Measured |
| Qwen-Image-Edit | ✕ Won't fit needs ~42 GB | VRAM-gated at this precision | ✓ Measured |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Stable Video Diffusion | 0.43 clips/min | 156 W78°C | ✓ Measured |
| LTX-Video (image to video) | ✕ Won't fit needs ~21 GB | VRAM-gated at this precision | ✓ Measured CPU offload |
| Wan 2.2 TI2V-5B (image to video) | ✕ Won't fit needs ~31 GB | VRAM-gated at this precision | ✓ Measured CPU offload |
| Stable Video Diffusion XT | ✕ Won't fit needs ~40 GB | VRAM-gated at this precision | ✓ Measured CPU offload |
| CogVideoX-5B I2V | ✕ Won't fit needs ~44 GB | VRAM-gated at this precision | ✓ Measured CPU offload |
| Workload | Result | Telemetry | Data |
|---|---|---|---|
| Wan 2.1 1.3B | 0.12 frames/s | 145 W86°C403.2 s/clip | ✓ Measured CPU offload |
| CogVideoX-2B | 0.09 frames/s | 155 W70°C554.3 s/clip | ✓ Measured CPU offload |
| LTX-Video (distilled) | ✕ Won't fit needs ~14 GB | VRAM-gated at this precision | ✓ Measured |
| Wan 2.2 5B (720p) | ✕ Won't fit needs ~18 GB | VRAM-gated at this precision | ✓ Measured |
| Architecture | Ampere (GA106) |
| CUDA cores | 3,584 |
| VRAM | 12GB GDDR6 |
| Memory bus | 192-bit |
| Memory bandwidth | 360 GB/s |
| Boost clock | 1,777 MHz |
| TDP | 170 W |
| Process | 8nm Samsung |
| Interface | PCIe 4.0 x16 |
| Release date | 2021-02-25 |
| Launch MSRP | $329 |
NVIDIA GeForce RTX 3060 scores 2.6/100, #63 of 102. It ran 4 of 12; 8 exceeded its 12GB. Every figure here is our own measurement.
100% = this card, AI & Machine Learning headline metric (AI Score). #24 of 61 desktop cards in this vertical.
| GPU | Relative | % | AI Score |
|---|---|---|---|
| GeForce RTX 5070 | 123% | 3.2 | |
| NVIDIA GeForce RTX 4070 Super | 119% | 3.1 | |
| NVIDIA GeForce RTX 4070 | 119% | 3.1 | |
| NVIDIA TITAN V | 112% | 2.9 | |
| NVIDIA GeForce RTX 3060 | 100% | 2.6 | |
| AMD Radeon RX 7900 XT | 96% | 2.5 | |
| AMD Radeon RX 7800 XT | 92% | 2.4 | |
| AMD Radeon RX 9070 XT | 92% | 2.4 | |
| AMD Radeon RX 9070 | 92% | 2.4 |
Same card, other workloads: NVIDIA GeForce RTX 3060 Gaming benchmarks
← All AI & Machine Learning GPU rankings
| Transistors | 12,000 million |
| Die size | 276 mm² |
| Process node | 8 nm |
| Fabricated by | Samsung |
| Transistor density | 43.5 million per mm² |
Denser than 78% of the 746 cards we have silicon data for. Density is the clearest measure of what a process node bought: a card that gained it without growing the die got its speed from the fab rather than the architecture.
Silicon figures from Wikipedia (CC BY-SA 4.0). Benchmarks on this page are our own. Compare every chip.
Whole-job timings, composed from our measured per-model results on this card.
| Workflow | Time | Energy | Basis |
|---|---|---|---|
| Full codebase review | 28.2 min | 69.16 Wh | measured |
Can't run: Animate a batch of images (needs Wan 2.2 TI2V-5B (image to video)), Product photo shoot (needs FLUX.1 Kontext dev), Photo restoration batch (needs FLUX.1 Kontext dev), Restore and enlarge photos (needs FLUX.1 Kontext dev), Character sheet, 12 poses (needs FLUX.1 dev), Short social clips (needs Qwen3 32B), 60-second AI short film (needs Qwen3 32B), 24-frame storyboard (needs Qwen3 32B), 6-panel comic page (needs Qwen3 32B), Long-form article batch (needs Llama 3.3 70B).
This card is $329 to buy. The cheapest listed rate on Vast.ai is $0.056/hour, but that is the floor: we budget $0.067/hour, a 20% premium, because idle time, storage and unavailable cheap instances all land on the same bill. At that rate buying wins after 4,896 GPU-hours. Below it you are paying for idle silicon.
| How you would use it | GPU-hours a year | Rental cost a year | Time to break even |
|---|---|---|---|
| 2 hours a day, hobby | 730 | $49 | 6.7 years |
| 8 hours a day, working on it | 2,920 | $196 | 1.7 years |
| 24/7, always-on agent | 8,760 | $589 | 6.7 months |
At hobby usage this card is very unlikely to pay for itself before it is superseded. Rent it. Rental figures include a 20% premium over the cheapest listed rate. Ignores electricity, resale and the fact that a rented card can be a newer one tomorrow.
Cheapest of the RunPod and Vast on-demand rates we see, sampled daily. Spot and interruptible pricing runs lower.