readygpu

NVIDIA GeForce RTX 5060 Ti 16GB vs NVIDIA GeForce RTX 5070

For running models locally, priced in the UK. At 8k context the first runs 40 models fully in memory, the second 31.

In short

The NVIDIA GeForce RTX 5060 Ti 16GB has more memory for models: 16 GB against 12 GB. At 8k context the NVIDIA GeForce RTX 5060 Ti 16GB runs 40 of the models we track fully in memory and the NVIDIA GeForce RTX 5070 31; only the NVIDIA GeForce RTX 5060 Ti 16GB holds Devstral Small 2 24B. On the models both run fully in memory, the NVIDIA GeForce RTX 5070 is about 1.5× as fast as the NVIDIA GeForce RTX 5060 Ti 16GB (estimated, median across models). In the UK the NVIDIA GeForce RTX 5060 Ti 16GB costs £613 at eBay and the NVIDIA GeForce RTX 5070 £592 at Amazon: the NVIDIA GeForce RTX 5070 is £21 cheaper.

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

NVIDIA GeForce RTX 5060 Ti 16GB

£613

eBay

Add to build
NVIDIA GeForce RTX 5070

£592

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 5060 Ti 16GBNVIDIA GeForce RTX 5070
GPUGeForce RTX 5060 Ti 16GBGeForce RTX 5070
Memory16 GB GDDR712 GB GDDR7
Memory bus128-bit192-bit
Memory bandwidth448 GB/s672 GB/s
FP16 compute47 TFLOPS62 TFLOPS
SoftwareCUDACUDA
Board power180 W250 W
PCIe generationGen 5Gen 5
PCIe lanesx8x16

What each runs

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

ModelNVIDIA GeForce RTX 5060 Ti 16GBNVIDIA GeForce RTX 5070
Devstral Small 2 24B18tok/sQ4_K_Moffload
gpt-oss 20B63tok/sMXFP4offload
Gemma 4 12B21tok/sQ8_041tok/sQ6_K
Qwen 3.5 9B28tok/sQ8_042tok/sQ8_0
Mistral Small 3.2 24B18tok/sQ4_K_Moffload
Qwen3 14B21tok/sQ6_K40tok/sQ4_K_M
Ministral 3 14B18tok/sQ8_038tok/sQ5_K_M
DeepSeek R1 0528 Qwen3 8B28tok/sQ8_042tok/sQ8_0
Qwen3 8B28tok/sQ8_042tok/sQ8_0
Phi-4 14B20tok/sQ6_K39tok/sQ4_K_M
Qwen 3.5 4B58tok/sQ8_087tok/sQ8_0
Ministral 3 8B27tok/sQ8_041tok/sQ8_0
Granite 4.2 8B26tok/sQ8_039tok/sQ8_0
Gemma 4 E4B33tok/sQ8_049tok/sQ8_0
LFM2.5 8B-A1B114tok/sQ8_0170tok/sQ8_0
Llama 3.1 8B36tok/sQ6_K54tok/sQ6_K
Qwen2.5 0.5B440tok/sQ8_0660tok/sQ8_0
Qwen3.5 0.8B298tok/sQ8_0447tok/sQ8_0
Qwen3.5 2B179tok/sQ5_K_M268tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B130tok/sQ8_0196tok/sQ8_0
MiniCPM5 2B92tok/sQ8_0137tok/sQ8_0
LFM2.5 2.6B82tok/sQ8_0123tok/sQ8_0
LFM2.5 VL 3B82tok/sQ8_0123tok/sQ8_0
Spark X2.5 4B82tok/smlx-4bit123tok/smlx-4bit
Kimi VL A3B Thinking 250676tok/sQ4_K_M115tok/sQ4_K_M
granite vision 4.1 4b65tok/sQ8_097tok/sQ8_0
granite 4.2 3b61tok/sQ8_091tok/sQ8_0
Kimi VL A3B60tok/smlx-6bitoffload
Mellum2.1 12B A2.5B Thinking59tok/sQ8_0113tok/sQ5_K_M
DeepSeek R1 Distill Qwen 7B32tok/sQ8_049tok/sQ8_0
GLM 4 9B 041432tok/smlx-5bit49tok/smlx-5bit
DeepSeek R1 Distill Llama 8B29tok/sQ8_043tok/sQ8_0
Ministral 3 8B Reasoning 251227tok/sQ8_041tok/sQ8_0
GLM 4.6V Flash27tok/sQ8_040tok/sQ8_0
GLM 4.1V 9B Thinking23tok/smlx-8bitoffload
DeepSeek R1 Distill Qwen 14B20tok/sQ6_K39tok/sQ4_K_M
Devstral Small 250718tok/sQ4_K_Moffload
Magistral Small 250618tok/sQ4_K_Moffload
Magistral Small 250718tok/sQ4_K_Moffload
Magistral Small 250918tok/sQ4_K_Moffload
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Boffloadwon't run
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadwon't run
Qwen 3.6 35B-A3Boffloadoffload
Qwen 3.5 27Boffloadoffload
Gemma 4 26B-A4Boffloadoffload
Qwen 3.5 35B-A3Boffloadoffload
GLM 4.7 Flashoffloadoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
LFM2.5 24B A2Boffloadoffload
granite 4.2 30boffloadoffload
Qwen3.8 27B OBLITERATEDoffloadoffload
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 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 4.5Vwon'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 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 Ti 16GB or the NVIDIA GeForce RTX 5070?
Choose the NVIDIA GeForce RTX 5060 Ti 16GB to run bigger models. Choose the NVIDIA GeForce RTX 5070 for speed. Choose the NVIDIA GeForce RTX 5070 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 5060 Ti 16GB or the NVIDIA GeForce RTX 5070?
At 8k context the NVIDIA GeForce RTX 5060 Ti 16GB runs 40 of the models we track fully in memory and the NVIDIA GeForce RTX 5070 31; only the NVIDIA GeForce RTX 5060 Ti 16GB holds Devstral Small 2 24B.
Which is faster for local AI, the NVIDIA GeForce RTX 5060 Ti 16GB or the NVIDIA GeForce RTX 5070?
On the models both run fully in memory, the NVIDIA GeForce RTX 5070 is about 1.5× as fast as the NVIDIA GeForce RTX 5060 Ti 16GB (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 5060 Ti 16GB and the NVIDIA GeForce RTX 5070?
In the UK the NVIDIA GeForce RTX 5060 Ti 16GB costs £613 at eBay and the NVIDIA GeForce RTX 5070 £592 at Amazon: the NVIDIA GeForce RTX 5070 is £21 cheaper.

More comparisons