Skip to content

NVIDIA GeForce RTX 5060 Ti 16GB

NVIDIA · 16GB GDDR7 · Can run 49 models

Buy Amazon
Manufacturer NVIDIA
VRAM 16 GB
Memory Type GDDR7
Architecture Blackwell
CUDA Cores 4,608
Tensor Cores 144
Bandwidth 448 GB/s
TDP 180W
MSRP $429
Released Apr 16, 2025

AI Notes

The RTX 5060 Ti 16GB is a strong mid-range option for local AI inference. With 16GB of GDDR7 VRAM, it can comfortably run 7B-parameter models at higher quantizations and 13B models at Q4. Its Blackwell tensor cores provide efficient inference performance for everyday AI workloads.

Compatible Models

Model Parameters Best Quant VRAM Used Fit Est. Speed
Qwen 3 0.6B 600M Q4_K_M 2.5 GB Runs ~179 tok/s
Gemma 3 1B 1B Q8_0 2 GB Runs ~224 tok/s
Llama 3.2 1B 1B Q8_0 3 GB Runs ~149 tok/s
DeepSeek R1 1.5B 1.5B Q8_0 3 GB Runs ~149 tok/s
Gemma 2 2B 2B Q8_0 4 GB Runs ~112 tok/s
Gemma 3n E2B 2B Q4_K_M 3.3 GB Runs ~136 tok/s
Llama 3.2 3B 3B Q8_0 5 GB Runs ~90 tok/s
Phi-3 Mini 3.8B 3.8B Q8_0 5.8 GB Runs ~77 tok/s
Phi-4 Mini 3.8B 3.8B Q4_K_M 4.5 GB Runs ~100 tok/s
Gemma 3 4B 4B Q4_K_M 5 GB Runs ~90 tok/s
Gemma 3n E4B 4B Q4_K_M 4.5 GB Runs ~100 tok/s
Qwen 3 4B 4B Q4_K_M 4.5 GB Runs ~100 tok/s
DeepSeek R1 7B 7B Q8_0 9 GB Runs ~50 tok/s
Falcon 3 7B 7B Q4_K_M 6.8 GB Runs ~66 tok/s
Mistral 7B 7B Q8_0 9 GB Runs ~50 tok/s
Qwen 2.5 7B 7B Q8_0 9 GB Runs ~50 tok/s
Qwen 2.5 Coder 7B 7B Q8_0 9 GB Runs ~50 tok/s
Qwen 2.5 VL 7B 7B Q4_K_M 7 GB Runs ~64 tok/s
Cogito 8B 8B Q4_K_M 7.5 GB Runs ~60 tok/s
DeepSeek R1 8B 8B Q4_K_M 7.5 GB Runs ~60 tok/s
Llama 3.1 8B 8B Q8_0 10 GB Runs ~45 tok/s
Nemotron 3 Nano 8B 8B Q4_K_M 7.5 GB Runs ~60 tok/s
Qwen 3 8B 8B Q4_K_M 7.5 GB Runs ~60 tok/s
Gemma 2 9B 9B Q8_0 11 GB Runs ~41 tok/s
Falcon 3 10B 10B Q4_K_M 8.5 GB Runs ~53 tok/s
Llama 3.2 Vision 11B 11B Q4_K_M 8.5 GB Runs ~53 tok/s
Gemma 3 12B 12B Q4_K_M 10.5 GB Runs ~43 tok/s
Mistral Nemo 12B 12B Q4_K_M 9.5 GB Runs ~47 tok/s
DeepSeek R1 14B 14B Q4_K_M 9.9 GB Runs ~45 tok/s
Phi-4 14B 14B Q4_K_M 9.9 GB Runs ~45 tok/s
Phi-4 Reasoning 14B 14B Q4_K_M 11 GB Runs ~41 tok/s
Qwen 2.5 14B 14B Q4_K_M 9.9 GB Runs ~45 tok/s
Qwen 2.5 Coder 14B 14B Q4_K_M 12 GB Runs ~37 tok/s
Qwen 3 14B 14B Q4_K_M 12 GB Runs ~37 tok/s
Codestral 22B 22B Q4_K_M 14.7 GB Runs (tight) ~30 tok/s
StarCoder2 15B 15B Q8_0 17 GB CPU Offload ~8 tok/s
Devstral 24B 24B Q4_K_M 17 GB CPU Offload ~8 tok/s
Magistral Small 24B 24B Q4_K_M 17 GB CPU Offload ~8 tok/s
Mistral Small 3.1 24B 24B Q4_K_M 18 GB CPU Offload ~8 tok/s
Gemma 2 27B 27B Q4_K_M 17.7 GB CPU Offload ~8 tok/s
Gemma 3 27B 27B Q4_K_M 20 GB CPU Offload ~7 tok/s
Qwen 3 30B-A3B (MoE) 30B Q4_K_M 22 GB CPU Offload ~6 tok/s
Cogito 32B 32B Q4_K_M 21.5 GB CPU Offload ~6 tok/s
DeepSeek R1 32B 32B Q4_K_M 20.7 GB CPU Offload ~7 tok/s
Qwen 2.5 32B 32B Q4_K_M 20.7 GB CPU Offload ~7 tok/s
Qwen 2.5 Coder 32B 32B Q4_K_M 23 GB CPU Offload ~6 tok/s
Qwen 3 32B 32B Q4_K_M 23 GB CPU Offload ~6 tok/s
QwQ 32B 32B Q4_K_M 21.5 GB CPU Offload ~6 tok/s
Command R 35B 35B Q4_K_M 22.5 GB CPU Offload ~6 tok/s
20 model(s) are too large for this hardware.