readygpu

NVIDIA GeForce RTX 4070 vs NVIDIA GeForce RTX 5070 Ti

For running models locally, priced in the US. At 32k context the first runs 28 models fully in memory, the second 36.

In short

The NVIDIA GeForce RTX 5070 Ti has more memory for models: 16 GB against 12 GB. At 32k context the NVIDIA GeForce RTX 5070 Ti runs 36 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 28; only the NVIDIA GeForce RTX 5070 Ti holds gpt-oss 20B. On the models both run fully in memory, the NVIDIA GeForce RTX 5070 Ti is about 1.8× as fast as the NVIDIA GeForce RTX 4070 (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 5070 Ti

$995

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 4070NVIDIA GeForce RTX 5070 Ti
GPUGeForce RTX 4070GeForce RTX 5070 Ti
Memory12 GB GDDR6X16 GB GDDR7
Memory bus192-bit256-bit
Memory bandwidth504.2 GB/s896 GB/s
FP16 compute29.146 TFLOPS88 TFLOPS
SoftwareCUDACUDA
Board power200 W300 W
PCIe generationGen 4Gen 5
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 4070NVIDIA GeForce RTX 5070 Ti
gpt-oss 20Boffload103tok/sMXFP4
Gemma 4 12B29tok/sQ6_K41tok/sQ8_0
Qwen 3.5 9B29tok/sQ8_052tok/sQ8_0
Ministral 3 14Boffload37tok/sQ5_K_M
Qwen3 14Boffload39tok/sQ4_K_M
DeepSeek R1 0528 Qwen3 8B29tok/sQ5_K_M41tok/sQ8_0
Qwen3 8B29tok/sQ5_K_M41tok/sQ8_0
Qwen 3.5 4B56tok/sQ8_099tok/sQ8_0
Ministral 3 8B29tok/sQ5_K_M41tok/sQ8_0
Granite 4.2 8B29tok/sQ4_K_M38tok/sQ8_0
Gemma 4 E4B34tok/sQ8_061tok/sQ8_0
LFM2.5 8B-A1B70tok/sQ8_0125tok/sQ8_0
Llama 3.1 8B29tok/sQ6_K51tok/sQ6_K
Qwen2.5 0.5B335tok/sQ8_0595tok/sQ8_0
Qwen3.5 0.8B254tok/sQ8_0450tok/sQ8_0
Qwen3.5 2B168tok/sQ5_K_M299tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B110tok/sQ8_0196tok/sQ8_0
MiniCPM5 2B77tok/sQ8_0136tok/sQ8_0
Mellum2.1 12B A2.5B Thinking73tok/sQ5_K_M105tok/sQ8_0
Spark X2.5 4B73tok/smlx-4bit129tok/smlx-4bit
LFM2.5 2.6B64tok/sQ8_0114tok/sQ8_0
LFM2.5 VL 3B64tok/sQ8_0114tok/sQ8_0
FrogNano 4B 260954tok/sQ8_097tok/sQ8_0
granite vision 4.1 4b50tok/sQ8_088tok/sQ8_0
granite 4.2 3b48tok/sQ8_085tok/sQ8_0
Ministral 3 3B Instruct 251244tok/sQ8_078tok/sQ8_0
GLM 4.6V Flash42tok/sQ4_K_M49tok/sQ8_0
GLM 4 9B 041433tok/smlx-5bit58tok/smlx-5bit
DeepSeek R1 Distill Qwen 7B31tok/sQ8_056tok/sQ8_0
Ministral 3 8B Reasoning 251229tok/sQ5_K_M41tok/sQ8_0
DeepSeek R1 Distill Llama 8B29tok/sQ6_K43tok/sQ8_0
Kimi VL A3B Thinking 2506offload113tok/sQ4_K_M
Kimi VL A3Boffload94tok/smlx-6bit
GLM 4.1V 9B Thinkingoffload42tok/smlx-8bit
Ministral 3 14B Reasoning 2512offload37tok/sQ5_K_M
DeepSeek R1 Distill Qwen 14Boffload36tok/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 4070 or the NVIDIA GeForce RTX 5070 Ti?
Choose the NVIDIA GeForce RTX 5070 Ti to run bigger models. Choose the NVIDIA GeForce RTX 5070 Ti for speed.
Which can run bigger models, the NVIDIA GeForce RTX 4070 or the NVIDIA GeForce RTX 5070 Ti?
At 32k context the NVIDIA GeForce RTX 5070 Ti runs 36 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 28; only the NVIDIA GeForce RTX 5070 Ti holds gpt-oss 20B.
Which is faster for local AI, the NVIDIA GeForce RTX 4070 or the NVIDIA GeForce RTX 5070 Ti?
On the models both run fully in memory, the NVIDIA GeForce RTX 5070 Ti is about 1.8× as fast as the NVIDIA GeForce RTX 4070 (estimated, median across models).

More comparisons

More hardware for local AI