readygpu

NVIDIA GeForce RTX 4070 vs NVIDIA GeForce RTX 5060 Ti 16GB

For running models locally, priced in the US. At 8k context the first runs 34 models fully in memory, the second 43.

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 43 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 34; 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 4070 is about 1.1× as fast as the NVIDIA GeForce RTX 5060 Ti 16GB (estimated, median across models).

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

NVIDIA GeForce RTX 4070

Not priced here

Add to build
NVIDIA GeForce RTX 5060 Ti 16GB

$618

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 4070NVIDIA GeForce RTX 5060 Ti 16GB
GPUGeForce RTX 4070GeForce RTX 5060 Ti 16GB
Memory12 GB GDDR6X16 GB GDDR7
Memory bus192-bit128-bit
Memory bandwidth504.2 GB/s448 GB/s
FP16 compute29.146 TFLOPS47 TFLOPS
SoftwareCUDACUDA
Board power200 W180 W
PCIe generationGen 4Gen 5
PCIe lanesx16x8

What each runs

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

ModelNVIDIA GeForce RTX 4070NVIDIA GeForce RTX 5060 Ti 16GB
Devstral Small 2 24Boffload18tok/sQ4_K_M
gpt-oss 20Boffload63tok/sMXFP4
Gemma 4 12B31tok/sQ6_K21tok/sQ8_0
Qwen 3.5 9B32tok/sQ8_028tok/sQ8_0
Mistral Small 3.2 24Boffload18tok/sQ4_K_M
Qwen3 14B30tok/sQ4_K_M21tok/sQ6_K
Ministral 3 14B29tok/sQ5_K_M18tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B32tok/sQ8_028tok/sQ8_0
Qwen3 8B32tok/sQ8_028tok/sQ8_0
Phi-4 14B30tok/sQ4_K_M20tok/sQ6_K
Qwen 3.5 4B65tok/sQ8_058tok/sQ8_0
Ministral 3 8B31tok/sQ8_027tok/sQ8_0
Granite 4.2 8B29tok/sQ8_026tok/sQ8_0
Gemma 4 E4B37tok/sQ8_033tok/sQ8_0
LFM2.5 8B-A1B128tok/sQ8_0114tok/sQ8_0
Llama 3.1 8B41tok/sQ6_K36tok/sQ6_K
Qwen2.5 0.5B495tok/sQ8_0440tok/sQ8_0
Qwen3.5 0.8B336tok/sQ8_0298tok/sQ8_0
Qwen3.5 2B201tok/sQ5_K_M179tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B147tok/sQ8_0130tok/sQ8_0
MiniCPM5 2B103tok/sQ8_092tok/sQ8_0
LFM2.5 2.6B93tok/sQ8_082tok/sQ8_0
LFM2.5 VL 3B93tok/sQ8_082tok/sQ8_0
Spark X2.5 4B92tok/smlx-4bit82tok/smlx-4bit
Kimi VL A3B Thinking 250686tok/sQ4_K_M76tok/sQ4_K_M
Mellum2.1 12B A2.5B Thinking85tok/sQ5_K_M59tok/sQ8_0
granite vision 4.1 4b73tok/sQ8_065tok/sQ8_0
Ministral 3 3B Instruct 251269tok/sQ8_061tok/sQ8_0
granite 4.2 3b69tok/sQ8_061tok/sQ8_0
FrogNano 4B 260963tok/sQ8_056tok/sQ8_0
DeepSeek R1 Distill Qwen 7B37tok/sQ8_032tok/sQ8_0
GLM 4 9B 041436tok/smlx-5bit32tok/smlx-5bit
DeepSeek R1 Distill Llama 8B33tok/sQ8_029tok/sQ8_0
Ministral 3 8B Reasoning 251231tok/sQ8_027tok/sQ8_0
GLM 4.6V Flash30tok/sQ8_027tok/sQ8_0
DeepSeek R1 Distill Qwen 14B30tok/sQ4_K_M20tok/sQ6_K
Ministral 3 14B Reasoning 251229tok/sQ5_K_M18tok/sQ8_0
Kimi VL A3Boffload60tok/smlx-6bit
GLM 4.1V 9B Thinkingoffload23tok/smlx-8bit
Devstral Small 2507offload18tok/sQ4_K_M
Magistral Small 2506offload18tok/sQ4_K_M
Magistral Small 2507offload18tok/sQ4_K_M
Magistral Small 2509offload18tok/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
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Kimi Linear 48B-A3Boffloadoffload
Qwen3 Coder 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
Gemma 3 27Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
LFM2.5 24B A2Boffloadoffload
Muse Glimmer 30Boffloadoffload
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 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 4070 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 4070 for speed.
Which can run bigger models, the NVIDIA GeForce RTX 4070 or the NVIDIA GeForce RTX 5060 Ti 16GB?
At 8k context the NVIDIA GeForce RTX 5060 Ti 16GB runs 43 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 34; only the NVIDIA GeForce RTX 5060 Ti 16GB holds Devstral Small 2 24B.
Which is faster for local AI, the NVIDIA GeForce RTX 4070 or the NVIDIA GeForce RTX 5060 Ti 16GB?
On the models both run fully in memory, the NVIDIA GeForce RTX 4070 is about 1.1× as fast as the NVIDIA GeForce RTX 5060 Ti 16GB (estimated, median across models).

More comparisons

More hardware for local AI