readygpu

NVIDIA GeForce RTX 4070 Ti Super vs NVIDIA GeForce RTX 5070

For running models locally, priced in the UK. At 8k context the first runs 16 models fully in memory, the second 13.

In short

The NVIDIA GeForce RTX 4070 Ti Super has more memory for models: 16 GB against 12 GB. At 8k context the NVIDIA GeForce RTX 4070 Ti Super runs 16 of the models we track fully in memory and the NVIDIA GeForce RTX 5070 13; only the NVIDIA GeForce RTX 4070 Ti Super holds Devstral Small 2 24B. On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Ti Super and the NVIDIA GeForce RTX 5070 are about as fast as each other (estimated). In the UK the NVIDIA GeForce RTX 4070 Ti Super costs £950 at eBay and the NVIDIA GeForce RTX 5070 £695 at eBay: the NVIDIA GeForce RTX 5070 is £255 cheaper.

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

NVIDIA GeForce RTX 4070 Ti Super

£950

eBay

Add to build
NVIDIA GeForce RTX 5070

£695

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 4070 Ti SuperNVIDIA GeForce RTX 5070
GPUGeForce RTX 4070 Ti SuperGeForce RTX 5070
Memory16 GB GDDR6X12 GB GDDR7
Memory bus256-bit192-bit
Memory bandwidth672 GB/s672 GB/s
FP16 compute88 TFLOPS62 TFLOPS
SoftwareCUDACUDA
Board power285 W250 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 4070 Ti SuperNVIDIA GeForce RTX 5070
Devstral Small 2 24B27tok/sQ4_K_Moffload
gpt-oss 20B95tok/sMXFP4offload
Gemma 4 12B32tok/sQ8_041tok/sQ6_K
Qwen 3.5 9B42tok/sQ8_042tok/sQ8_0
Mistral Small 3.2 24B27tok/sQ4_K_Moffload
Qwen3 14B31tok/sQ6_K40tok/sQ4_K_M
Ministral 3 14B27tok/sQ8_038tok/sQ5_K_M
DeepSeek R1 0528 Qwen3 8B42tok/sQ8_042tok/sQ8_0
Qwen3 8B42tok/sQ8_042tok/sQ8_0
Phi-4 14B30tok/sQ6_K39tok/sQ4_K_M
Qwen 3.5 4B87tok/sQ8_087tok/sQ8_0
Ministral 3 8B41tok/sQ8_041tok/sQ8_0
Granite 4.2 8B39tok/sQ8_039tok/sQ8_0
Gemma 4 E4B49tok/sQ8_049tok/sQ8_0
LFM2.5 8B-A1B170tok/sQ8_0170tok/sQ8_0
Llama 3.1 8B54tok/sQ6_K54tok/sQ6_K
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
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

Questions

Which is better for local AI, the NVIDIA GeForce RTX 4070 Ti Super or the NVIDIA GeForce RTX 5070?
Choose the NVIDIA GeForce RTX 4070 Ti Super to run bigger models. Choose the NVIDIA GeForce RTX 5070 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 4070 Ti Super or the NVIDIA GeForce RTX 5070?
At 8k context the NVIDIA GeForce RTX 4070 Ti Super runs 16 of the models we track fully in memory and the NVIDIA GeForce RTX 5070 13; only the NVIDIA GeForce RTX 4070 Ti Super holds Devstral Small 2 24B.
Which is faster for local AI, the NVIDIA GeForce RTX 4070 Ti Super or the NVIDIA GeForce RTX 5070?
On the models both run fully in memory, the NVIDIA GeForce RTX 4070 Ti Super and the NVIDIA GeForce RTX 5070 are about as fast as each other (estimated).
What is the price difference between the NVIDIA GeForce RTX 4070 Ti Super and the NVIDIA GeForce RTX 5070?
In the UK the NVIDIA GeForce RTX 4070 Ti Super costs £950 at eBay and the NVIDIA GeForce RTX 5070 £695 at eBay: the NVIDIA GeForce RTX 5070 is £255 cheaper.

More comparisons