readygpu

NVIDIA GeForce RTX 5060 vs NVIDIA GeForce RTX 5060 Ti 16GB

For running models locally, priced in Germany. At 32k context the first runs 18 models fully in memory, the second 37.

In short

The NVIDIA GeForce RTX 5060 Ti 16GB has more memory for models: 16 GB against 8 GB. At 32k context the NVIDIA GeForce RTX 5060 Ti 16GB runs 37 of the models we track fully in memory and the NVIDIA GeForce RTX 5060 18; only the NVIDIA GeForce RTX 5060 Ti 16GB holds gpt-oss 20B. On the models both run fully in memory, the NVIDIA GeForce RTX 5060 and the NVIDIA GeForce RTX 5060 Ti 16GB are about as fast as each other (estimated). In Germany the NVIDIA GeForce RTX 5060 costs 449 € at eBay and the NVIDIA GeForce RTX 5060 Ti 16GB 473 € at Amazon: the NVIDIA GeForce RTX 5060 is 24 € cheaper.

Updated . Speeds are estimates; how they are worked out.

NVIDIA GeForce RTX 5060

449 €

eBay

Add to build
NVIDIA GeForce RTX 5060 Ti 16GB

473 €

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 5060NVIDIA GeForce RTX 5060 Ti 16GB
GPUGeForce RTX 5060GeForce RTX 5060 Ti 16GB
Memory8 GB GDDR716 GB GDDR7
Memory bus128-bit128-bit
Memory bandwidth448 GB/s448 GB/s
FP16 compute19.177 TFLOPS47 TFLOPS
SoftwareCUDACUDA
Board power145 W180 W
PCIe generationGen 5Gen 5
PCIe lanesx8x8

What each runs

Estimated decode speed with the most precise quant that fits each one est.

ModelNVIDIA GeForce RTX 5060NVIDIA GeForce RTX 5060 Ti 16GB
gpt-oss 20Boffload52tok/sMXFP4
Gemma 4 12Boffload21tok/sQ8_0
Qwen 3.5 9B41tok/sQ4_K_M26tok/sQ8_0
Ministral 3 14Boffload19tok/sQ5_K_M
Qwen3 14Boffload19tok/sQ4_K_M
DeepSeek R1 0528 Qwen3 8Boffload21tok/sQ8_0
Qwen3 8Boffload21tok/sQ8_0
Qwen 3.5 4B50tok/sQ8_050tok/sQ8_0
Ministral 3 8Boffload20tok/sQ8_0
Granite 4.2 8Boffload19tok/sQ8_0
Gemma 4 E4B43tok/sQ5_K_M30tok/sQ8_0
LFM2.5 8B-A1B74tok/sMXFP462tok/sQ8_0
Llama 3.1 8Boffload26tok/sQ6_K
Qwen2.5 0.5B298tok/sQ8_0298tok/sQ8_0
Qwen3.5 0.8B225tok/sQ8_0225tok/sQ8_0
Qwen3.5 2B150tok/sQ5_K_M150tok/sQ5_K_M
LFM3 1.7B123tok/sQ8_0123tok/sQ8_0
DeepSeek R1 Distill Qwen 1.5B98tok/sQ8_098tok/sQ8_0
MiniCPM5 2B68tok/sQ8_068tok/sQ8_0
Spark X2.5 4B65tok/smlx-4bit65tok/smlx-4bit
LFM2.5 2.6B57tok/sQ8_057tok/sQ8_0
LFM2.5 VL 3B57tok/sQ8_057tok/sQ8_0
FrogNano 4B 260948tok/sQ8_048tok/sQ8_0
granite vision 4.1 4b44tok/sQ8_044tok/sQ8_0
Ministral 3 3B Instruct 251244tok/sQ6_K39tok/sQ8_0
DeepSeek R1 Distill Qwen 7B42tok/sQ4_K_M28tok/sQ8_0
granite 4.2 3b42tok/sQ8_042tok/sQ8_0
Mellum2.1 12B A2.5B Thinkingoffload53tok/sQ8_0
GLM 4.6V Flashoffload25tok/sQ8_0
Kimi VL A3B Thinking 2506offload57tok/sQ4_K_M
GLM 4 9B 0414offload29tok/smlx-5bit
Kimi VL A3Boffload47tok/smlx-6bit
DeepSeek R1 Distill Llama 8Boffload22tok/sQ8_0
Ministral 3 8B Reasoning 2512offload20tok/sQ8_0
GLM 4.1V 9B Thinkingoffload21tok/smlx-8bit
Ministral 3 14B Reasoning 2512offload19tok/sQ5_K_M
DeepSeek R1 Distill Qwen 14Boffload18tok/sQ4_K_M
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Bwon't runoffload
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Bwon't runoffload
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Gemma 4 26B-A4Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Devstral Small 2 24Boffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
Mistral Small 3.2 24Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
Phi-4 14Boffloadoffload
LFM2.5 24B A2Boffloadoffload
Muse Glimmer 30Boffloadoffload
Devstral Small 2507offloadoffload
Magistral Small 2506offloadoffload
Magistral Small 2507offloadoffload
Magistral Small 2509offloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
granite 4.2 30boffloadoffload
DeepSeek V4 Flashwon't runwon't run
GLM 5.3 Flashwon't runwon't run
Qwen 3.8 Flash Nextwon't runwon't run
MiniMax M2.7won't runwon't run
Nemotron 3 Super 120B-A12Bwon't runwon't run
Qwen3 Coder Nextwon't runwon't run
gpt-oss 120Bwon't runwon't run
GLM 4.5 Airwon't runwon't run
Qwen3 Next 80B-A3Bwon't runwon't run
Llama 3.3 70Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won't runwon't run
DeepSeek R1 Distill Llama 70Bwon't runwon't run
DeepSeek R1 Zerowon't runwon't run
DeepSeek V3won't runwon't run
DeepSeek V3 0324won't runwon't run
DeepSeek V3.1won't runwon't run
DeepSeek V3.1 Terminuswon't runwon't run
DeepSeek V3.2won't runwon't run
DeepSeek V4 Flash 0731won't runwon't run
DeepSeek V4 Flash Vision Expwon't runwon't run
Devstral 2 123B Instruct 2512won't runwon't run
GLM 4.5won't runwon't run
GLM 4.5Vwon't runwon't run
GLM 4.6won't runwon't run
GLM 4.6Vwon't runwon't run
GLM 4.7won't runwon't run
GLM 5won't runwon't run
GLM 5.1won't runwon't run
GLM 5.2won't runwon't run
GLM 5.3won't runwon't run
Kimi Dev 72Bwon't runwon't run
Kimi K2won't runwon't run
Kimi K2 Instruct 0905won't runwon't run
Kimi K2 Thinkingwon't runwon't run
Kimi K2.5won't runwon't run
MiniMax M2won't runwon't run
MiniMax M2.1won't runwon't run
MiniMax M2.5won't runwon't run
MiniMax M3won't runwon't run
Mistral Medium 3.5 128Bwon't runwon't run

Questions

Which is better for local AI, the NVIDIA GeForce RTX 5060 or the NVIDIA GeForce RTX 5060 Ti 16GB?
Choose the NVIDIA GeForce RTX 5060 Ti 16GB to run bigger models. Choose the NVIDIA GeForce RTX 5060 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 5060 or the NVIDIA GeForce RTX 5060 Ti 16GB?
At 32k context the NVIDIA GeForce RTX 5060 Ti 16GB runs 37 of the models we track fully in memory and the NVIDIA GeForce RTX 5060 18; only the NVIDIA GeForce RTX 5060 Ti 16GB holds gpt-oss 20B.
Which is faster for local AI, the NVIDIA GeForce RTX 5060 or the NVIDIA GeForce RTX 5060 Ti 16GB?
On the models both run fully in memory, the NVIDIA GeForce RTX 5060 and the NVIDIA GeForce RTX 5060 Ti 16GB are about as fast as each other (estimated).
What is the price difference between the NVIDIA GeForce RTX 5060 and the NVIDIA GeForce RTX 5060 Ti 16GB?
In Germany the NVIDIA GeForce RTX 5060 costs 449 € at eBay and the NVIDIA GeForce RTX 5060 Ti 16GB 473 € at Amazon: the NVIDIA GeForce RTX 5060 is 24 € cheaper.

More comparisons

More hardware for local AI