Hardware
GeForce RTX 3060 12GB
Card only. 12 GB covers 7B–8B and is tight for 14B Q4.
Memory
12 GB VRAMBandwidth
360 GB/sBandwidth source is not stored.
Price
$313€280
14 Oct 2026
price unverifiedWhich models fit
Estimate at 8,192 tokens, or the model's maximum when that is shorter. full means the formula fits in usable memory. offload means GPU plus system RAM. no means it does not fit. This is not a measured file.
| Model | Q4estimate | Q5estimate | Q8estimate | FP16estimate |
|---|---|---|---|---|
| Llama 3.2 3B | full | full | full | full |
| Llama 3.1 8B | full | full | full | no |
| Mistral 7B v0.3 | full | full | full | no |
| Gemma 2 9B | full | full | no | no |
| Qwen2.5 14B | full | no | no | no |
| Phi-4 14B | full | no | no | no |
| Gemma 2 27B | no | no | no | no |
| Qwen2.5 32B | no | no | no | no |
| Llama 3.3 70B | no | no | no | no |
| Qwen2.5 72B | no | no | no | no |
| DeepSeek-R1-Distill 70B | no | no | no | no |