Graphics cards
Which AI models run on the RTX 3060 (12 GB)?
The RTX 3060 (12 GB) has 12 GB of memory, about 11.0 GB of it usable for a model, and 360 GB/s of memory bandwidth. 45 of the 110 models in our catalog run on it at 4-bit or better.
Data as of 2 November 2026
Models that run on it
| Model | Best build | Memory | Speed |
|---|---|---|---|
| Nemotron Nano 9B v29B | Q8_0 | 10.8 GB | ~21 tok/s our est. |
| Qwen3.5 9B Instruct9B | Q4_K_M | 8.2 GB | ~53 tok/s ModelFit est. |
| Qwen2.5 7B Instruct7B | Q4_K_M | 6.6 GB | ~58 tok/s ModelFit est. |
| Gemma 3 4B Instruct4B | Q8_0 | 5.0 GB | ~61 tok/s ModelFit est. |
| Ministral 3 14B13.5B | Q4_K_M | 10.3 GB | ~30 tok/s ModelFit est. |
| Mellum2.1 12B-A2.5B Thinking12.1B MoE | Q4_K_M | 9.3 GB | ~118 tok/s our est. |
| Mistral Nemo 12B12B | Q4_K_M | 10.7 GB | ~38 tok/s ModelFit est. |
| Gemma 3 12B Instruct12B | Q4_K_M | 10.7 GB | ~35 tok/s ModelFit est. |
| Gemma 4 12B12B | Q4_K_M | 9.2 GB | ~35 tok/s ModelFit est. |
| GLM-4-9B-Chat9.4B | Q4_K_M | 7.5 GB | ~45 tok/s ModelFit est. |
| Gemma 2 9B Instruct9B | Q4_K_M | 8.2 GB | ~38 tok/s ModelFit est. |
| Ornith 1.0 9B9B | Q4_K_M | 6.7 GB | ~53 tok/s ModelFit est. |
| MiMo-V2.6-Distill-Qwen-9B9B | Q4_K_M | 6.9 GB | ~51 tok/s ModelFit est. |
| Jebadiah 9B9B | Q5_K_M | 7.8 GB | ~46 tok/s ModelFit est. |
| Granite 4.2 8B8.8B | Q4_K_M | 6.1 GB | ~47 tok/s ModelFit est. |
| Granite Switch 4.1 8B8.8B | Q4_K_M | 7.6 GB | ~39 tok/s ModelFit est. |
| MiniCPM-V 4.5 8B8.7B | Q4_K_M | 6.8 GB | ~51 tok/s ModelFit est. |
| Ministral 3 8B8.4B | Q4_K_M | 7.1 GB | ~44 tok/s ModelFit est. |
| LFM2.5 8B-A1B8.3B MoE | Q4_K_M | 6.6 GB | ~139 tok/s ModelFit est. |
| Llama 3.1 8B Instruct8B | Q8_0 | 9.2 GB | ~33 tok/s ModelFit est. |
| Qwen3 8B8B | Q8_0 | 9.3 GB | ~32 tok/s ModelFit est. |
| Granite 4.1 8B Instruct8B | Q4_K_M | 6.6 GB | ~45 tok/s ModelFit est. |
| Mistral 7B Instruct7B | Q8_0 | 8.4 GB | ~34 tok/s ModelFit est. |
| Qwen2.5 Coder 7B7B | Q4_K_M | 6.6 GB | ~58 tok/s ModelFit est. |
| DeepSeek-R1 Distill Qwen 7B7B | Q8_0 | 8.7 GB | ~36 tok/s ModelFit est. |
| Gemma 4 E4B4.5B | Q8_0 | 8.7 GB | ~53 tok/s ModelFit est. |
| Qwen3.5 4B Instruct4B | Q8_0 | 5.4 GB | ~58 tok/s ModelFit est. |
| NVIDIA Nemotron 3.5 Bolt E4B4B | Q4_K_M | 9.1 GB | ~67 tok/s ModelFit est. |
| Phi-3 Mini 3.8B3.8B | Q4_K_M | 4.3 GB | ~62 tok/s our est. |
| Phi-4 Mini 3.8B3.8B | Q8_0 | 4.9 GB | ~58 tok/s ModelFit est. |
| Granite 4.2 3B3.7B | Q4_K_M | 3.2 GB | ~102 tok/s ModelFit est. |
| Ministral 3 3B3.4B | Q4_K_M | 4.1 GB | ~76 tok/s ModelFit est. |
| Qwen2.5 3B Instruct3B | Q4_K_M | 3.6 GB | ~116 tok/s ModelFit est. |
| Llama 3.2 3B Instruct3B | Q4_K_M | 3.6 GB | ~99 tok/s ModelFit est. |
| Granite 4.1 3B Instruct3B | Q4_K_M | 3.0 GB | ~101 tok/s ModelFit est. |
| Gemma 4 E2B2.3B | Q8_0 | 5.7 GB | ~116 tok/s ModelFit est. |
| Gemma 2 2B Instruct2B | Q4_K_M | 2.8 GB | ~112 tok/s ModelFit est. |
| Qwen3.5 2B Instruct2B | Q4_K_M | 2.8 GB | ~117 tok/s ModelFit est. |
| LFM3 1.7B1.73B | Q4_K_M | 2.1 GB | ~183 tok/s ModelFit est. |
| Qwen2.5 1.5B Instruct1.5B | Q4_K_M | 2.5 GB | ~188 tok/s ModelFit est. |
| Llama 3.2 1B Instruct1B | Q4_K_M | 2.0 GB | ~210 tok/s ModelFit est. |
| Gemma 3 1B Instruct1B | Q8_0 | 2.0 GB | ~189 tok/s ModelFit est. |
| Qwen3.5 0.8B Instruct0.8B | Q4_K_M | 1.8 GB | ~223 tok/s ModelFit est. |
| Qwen2.5 0.5B Instruct0.5B | Q4_K_M | 1.8 GB | ~325 tok/s ModelFit est. |
| SmolLM2 360M0.36B | Q4_K_M | 1.5 GB | ~217 tok/s ModelFit est. |
Speeds come from ModelFit's estimates (CC BY 4.0) where it covers the model, otherwise from our bandwidth formula. Method
Too big for this machine
Qwen2.5 14B Instruct (12.3 GB), Phi-3 Medium 14B (12.3 GB), Qwen2.5 Coder 14B (12.3 GB), Qwen3 14B (12.3 GB), DeepSeek-R1 Distill Qwen 14B (12.3 GB), Phi-4 14B (12.8 GB), gpt-oss-20b (15.1 GB), LFM2 24B-A2B Instruct (15.3 GB), Mistral Small 3.1 (16.4 GB), Devstral Small 2 24B (16.6 GB), Gemma 4 26B-A4B (17.4 GB), Qwen3.5 27B Instruct (17.4 GB) and more.
Questions
What is the best AI model for the RTX 3060 (12 GB)?
Qwen3.5 9B Instruct at Q4_K_M: the largest model on our shortlist of current models that runs at 4-bit or better at a usable speed (about 53 tok/s, ModelFit est.).
How much memory can a model use on the RTX 3060 (12 GB)?
About 11.0 GB of the 12 GB.
How fast is the RTX 3060 (12 GB) for local LLMs?
Decode speed is limited by memory bandwidth: 360 GB/s. A model that reads 10 GB per token runs at under 36 tokens per second.