Which AI models can the NVIDIA RTX 5060 Ti 16GB run?
- 16 GB VRAM
- 448 GB/s bandwidth
- NVIDIA
Every model we track, checked against the NVIDIA RTX 5060 Ti 16GB at 8K context.
| Model | Runs? | Best fit |
|---|---|---|
| Llama 3.2 1B | Yes | FP16 · ~3.3 GB · ~108 tok/s |
| Llama 3.2 3B | Yes | FP16 · ~8 GB · ~42 tok/s |
| Llama 3.1 8B | Yes | Q8_0 · ~10.2 GB · ~32 tok/s |
| Llama 3.1 70B | No | Needs ~46.1 GB at Q4_K_M; 16 GB available |
| Qwen2.5 7B | Yes | Q8_0 · ~9.2 GB · ~33 tok/s |
| Qwen2.5 14B | Yes | Q6_K · ~14.3 GB · ~22 tok/s |
| Qwen2.5 32B | Yes, with heavy quantization | Q2_K · ~15 GB · ~22 tok/s |
| Qwen2.5 72B | No | Needs ~47.4 GB at Q4_K_M; 16 GB available |
| Qwen3 8B | Yes | Q8_0 · ~10.5 GB · ~31 tok/s |
| Qwen3 30B-A3B | Yes, with heavy quantization | Q2_K · ~12.8 GB · ~217 tok/s |
| DeepSeek R1 Distill Qwen 32B | Yes, with heavy quantization | Q2_K · ~15 GB · ~22 tok/s |
| Mistral 7B v0.3 | Yes | Q8_0 · ~9.4 GB · ~35 tok/s |
| Mistral Nemo 12B | Yes | Q8_0 · ~14.9 GB · ~21 tok/s |
| Mistral Small 24B | Yes, with heavy quantization | Q3_K_M · ~13.5 GB · ~23 tok/s |
| Mixtral 8x7B | No | Needs ~30 GB at Q4_K_M; 16 GB available |
| Gemma 2 9B | Yes | Q8_0 · ~13.2 GB · ~27 tok/s |
| Gemma 2 27B | Yes, with heavy quantization | Q2_K · ~13.9 GB · ~26 tok/s |
| Gemma 3 4B | Yes | FP16 · ~10.3 GB · ~31 tok/s |
| Gemma 3 12B | Yes | Q6_K · ~13.8 GB · ~27 tok/s |
| Gemma 3 27B | Yes, with heavy quantization | Q2_K · ~15 GB · ~26 tok/s |
| Phi-3.5 Mini 3.8B | Yes | FP16 · ~11.5 GB · ~35 tok/s |
| Phi-4 14B | Yes | Q6_K · ~14.3 GB · ~22 tok/s |
| Qwen3 4B | Yes | FP16 · ~9.8 GB · ~33 tok/s |
| Qwen3 14B | Yes | Q6_K · ~14.1 GB · ~22 tok/s |
| Qwen3 32B | Yes, with heavy quantization | Q2_K · ~15 GB · ~22 tok/s |
| Qwen3 Coder 30B-A3B | Yes, with heavy quantization | Q2_K · ~12.8 GB · ~217 tok/s |
| gpt-oss 20B | Yes | Q5_K_M · ~15.9 GB · ~105 tok/s |
| gpt-oss 120B | No | Needs ~72 GB at Q4_K_M; 16 GB available |
| Llama 4 Scout 17B-16E | No | Needs ~68.3 GB at Q4_K_M; 16 GB available |
Run it in the cloud
Need more than 16 GB? Rent a bigger GPU by the hour.
Rent a cloud GPU by the hour. No upfront cost, cancel any time.