Hardware profile
NVIDIA RTX 4060 Ti · 16 GB
32 GB system memory · 16 GB VRAM
Platform Windows
Available for models 16 GB
Backends Ollama, llama.cpp, CUDA
VRAM is the main constraint; system memory is not the same as available GPU memory.
Model fit
| Model | Minimum | Result |
|---|---|---|
| gpt-oss-20b | 14 GB | Tight fit |
| Qwen3.6 35B-A3B | 25 GB | Not recommended |
| Qwen3.8 27B | 20 GB | Not recommended |
| Gemma 4 12B Unified | 10 GB | Fits |
| Gemma 4 E4B | 8 GB | Fits |
| Gemma 4 31B | 23 GB | Not recommended |
| gpt-oss-120b | 66 GB | Not recommended |
| DeepSeek V4.1 Flash | 234 GB | Not recommended |
| Llama 3.2 3B | 4 GB | Fits |
| Qwen3 8B | 8 GB | Fits |
| Gemma 3 4B | 6 GB | Fits |
| Phi-4 Mini | 5 GB | Fits |
| Mistral 7B | 8 GB | Fits |
| DeepSeek R1 8B | 8 GB | Fits |
Source
https://www.nvidia.com/en-us/geforce/graphics-cards/40-series/rtx-4060-4060ti/