What AI models run on the RTX 5060 Ti 16GB?
The RTX 5060 Ti 16GB has 16 GB of VRAM (448 GB/s). About 15.2 GB is usable for a model. 194 of 285 open models we track fit at 8K context.
This card has 16 GB of VRAM. See every model that fits in 16 GB VRAM. Other 16 GB hardware: RTX 4060 Ti 16GB, RTX 4070 Ti Super, RTX 4080, RTX 4080 Super, RTX 5070 Ti, RTX 5080, RX 7800 XT, RX 7900 GRE.
Models that fit, largest first
Just too big at 4-bit
These need up to 35% more memory than the RTX 5060 Ti 16GB has at Q4_K_M and 8K context. A smaller quant or shorter context may work.
| Model | Q4_K_M needs | Short by |
|---|---|---|
| Trinity Mini | 15.8 GB | 0.6 GB |
| GLiDE 27B | 16.2 GB | 1.0 GB |
| MiniMax H3 Image PE | 16.8 GB | 1.6 GB |
| Qwen3.8 27B | 16.8 GB | 1.6 GB |
| Qwen3.5 27B | 17.0 GB | 1.8 GB |
| Qwen3.6 27B | 17.0 GB | 1.8 GB |
| diffusiongemma 26B A4B it | 17.1 GB | 1.9 GB |
| gemma 4 26B A4B it | 17.2 GB | 2.0 GB |
| gemma 3 27b it | 17.3 GB | 2.1 GB |
| Arete 27B | 17.4 GB | 2.2 GB |
| Muse Glimmer 30B | 17.9 GB | 2.7 GB |
| GLM 4.7 Flash | 18.2 GB | 3.0 GB |
| Hy Memory 30B A3B | 18.5 GB | 3.3 GB |
| Qwen3 Coder 30B A3B Instruct | 18.7 GB | 3.5 GB |
| granite 4.0 h small | 18.9 GB | 3.7 GB |
Questions
What is the biggest model that runs on the RTX 5060 Ti 16GB?
Of the models we track, the largest that fits at 8K context is flint (40B) at Q2_K, needing about 14.8 GB.
How much of the RTX 5060 Ti 16GB's memory can a model use?
About 15.2 GB: we assume 95% of the 16 GB is usable after driver and display overhead.
Spec source: NVIDIA specifications. Model data: Hugging Face Hub API. Speed is a bandwidth ceiling (bandwidth ÷ bytes read per token), not a benchmark. Methodology · Report an error.