readygpu

AMD Radeon AI PRO R9700 vs NVIDIA GeForce RTX 4070 Super

For running models locally, priced in Germany. At 8k context the first runs 58 models fully in memory, the second 32.

In short

The AMD Radeon AI PRO R9700 has more memory for models: 32 GB against 12 GB. At 8k context the AMD Radeon AI PRO R9700 runs 58 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 Super 32; only the AMD Radeon AI PRO R9700 holds Qwen 3.8 27B. On the models both run fully in memory, the AMD Radeon AI PRO R9700 is about 1.1× as fast as the NVIDIA GeForce RTX 4070 Super (estimated, median across models). In Germany the AMD Radeon AI PRO R9700 costs 2.390 € at eBay and the NVIDIA GeForce RTX 4070 Super 1.800 € at eBay: the NVIDIA GeForce RTX 4070 Super is 590 € cheaper.

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

AMD Radeon AI PRO R9700

2.390 €

eBay

Add to build
NVIDIA GeForce RTX 4070 Super

1.800 €

eBay

Add to build

Specifications

SpecAMD Radeon AI PRO R9700NVIDIA GeForce RTX 4070 Super
GPURadeon AI PRO R9700GeForce RTX 4070 Super
Memory32 GB GDDR612 GB GDDR6X
Memory bus256-bit192-bit
Memory bandwidth640 GB/s504 GB/s
FP16 compute191 TFLOPS71 TFLOPS
SoftwareROCmCUDA
Board power300 W220 W
PCIe generationGen 5Gen 4
PCIe lanesx16x16

What each runs

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

ModelAMD Radeon AI PRO R9700NVIDIA GeForce RTX 4070 Super
Qwen 3.8 27B12tok/sQ8_0offload
Qwen 3.6 27B12tok/sQ8_0offload
Gemma 4 31B13tok/sQ6_Koffload
Qwen 3.6 35B-A3B75tok/sQ6_Koffload
Qwen 3.5 27B12tok/sQ8_0offload
Gemma 4 26B-A4B47tok/sQ8_0offload
Qwen 3.5 35B-A3B80tok/sQ6_Koffload
GLM 4.7 Flash37tok/sQ8_0offload
Devstral Small 2 24B13tok/sQ8_0offload
Nemotron 3.5 Lightning 30B-A3B71tok/sUD-Q5_K_Moffload
Kimi Linear 48B-A3B109tok/sQ4_K_Moffload
gpt-oss 20B80tok/sMXFP4offload
Qwen3 Coder 30B-A3B65tok/sQ6_Koffload
Qwen3 32B12tok/sQ6_Koffload
Gemma 4 12B27tok/sQ8_031tok/sQ6_K
Qwen 3.5 9B36tok/sQ8_032tok/sQ8_0
Mistral Small 3.2 24B13tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B12tok/sQ6_Koffload
Gemma 3 27B12tok/sQ8_0offload
Ministral 3 14B22tok/sQ8_029tok/sQ5_K_M
Qwen3 14B21tok/sQ8_030tok/sQ4_K_M
DeepSeek R1 0528 Qwen3 8B36tok/sQ8_032tok/sQ8_0
Qwen3 8B36tok/sQ8_032tok/sQ8_0
Phi-4 14B20tok/sQ8_030tok/sQ4_K_M
Qwen 3.5 4B73tok/sQ8_065tok/sQ8_0
Ministral 3 8B35tok/sQ8_031tok/sQ8_0
Granite 4.2 8B33tok/sQ8_029tok/sQ8_0
Gemma 4 E4B42tok/sQ8_037tok/sQ8_0
LFM2.5 8B-A1B144tok/sQ8_0128tok/sQ8_0
Llama 3.1 8B46tok/sQ6_K41tok/sQ6_K
Qwen2.5 0.5B557tok/sQ8_0495tok/sQ8_0
Qwen3.5 0.8B378tok/sQ8_0336tok/sQ8_0
Qwen3.5 2B226tok/sQ5_K_M201tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B165tok/sQ8_0147tok/sQ8_0
MiniCPM5 2B116tok/sQ8_0103tok/sQ8_0
LFM2.5 2.6B104tok/sQ8_093tok/sQ8_0
LFM2.5 VL 3B104tok/sQ8_093tok/sQ8_0
Spark X2.5 4B104tok/smlx-4bit92tok/smlx-4bit
granite vision 4.1 4b82tok/sQ8_073tok/sQ8_0
granite 4.2 3b77tok/sQ8_069tok/sQ8_0
LFM2.5 24B A2B76tok/sQ8_0offload
Mellum2.1 12B A2.5B Thinking75tok/sQ8_085tok/sQ5_K_M
FrogNano 4B 260971tok/sQ8_063tok/sQ8_0
Kimi VL A3B Thinking 250663tok/sQ8_086tok/sQ4_K_M
Kimi VL A3B60tok/smlx-8bitoffload
DeepSeek R1 Distill Qwen 7B41tok/sQ8_037tok/sQ8_0
GLM 4 9B 041441tok/smlx-5bit36tok/smlx-5bit
DeepSeek R1 Distill Llama 8B37tok/sQ8_033tok/sQ8_0
Ministral 3 8B Reasoning 251235tok/sQ8_031tok/sQ8_0
GLM 4.6V Flash34tok/sQ8_030tok/sQ8_0
GLM 4.1V 9B Thinking29tok/smlx-8bitoffload
DeepSeek R1 Distill Qwen 14B20tok/sQ8_030tok/sQ4_K_M
Qwen3.8 27B OBLITERATED17tok/smlx-4bitoffload
Devstral Small 250713tok/sQ8_0offload
Magistral Small 250613tok/sQ8_0offload
Magistral Small 250713tok/sQ8_0offload
Magistral Small 250913tok/sQ8_0offload
granite 4.2 30b13tok/sQ6_Koffload
Qwen 3.5 122B-A10Boffloadwon't run
Qwen3 Coder Nextoffloadwon't run
Nemotron 3 Super 120B-A12Boffloadwon't run
Mistral Small 4 119Boffloadwon't run
GLM 4.5 Airoffloadwon't run
Qwen3 Next 80B-A3Boffloadwon't run
Llama 3.3 70Boffloadwon't run
DeepSeek R1 Distill Llama 70Boffloadwon't run
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
gpt-oss 120Bwon't runwon't run
DeepSeek R1won't runwon't run
DeepSeek R1 0528won'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 4.5won'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 AMD Radeon AI PRO R9700 or the NVIDIA GeForce RTX 4070 Super?
Choose the AMD Radeon AI PRO R9700 to run bigger models. Choose the AMD Radeon AI PRO R9700 for speed. Choose the NVIDIA GeForce RTX 4070 Super to spend less.
Which can run bigger models, the AMD Radeon AI PRO R9700 or the NVIDIA GeForce RTX 4070 Super?
At 8k context the AMD Radeon AI PRO R9700 runs 58 of the models we track fully in memory and the NVIDIA GeForce RTX 4070 Super 32; only the AMD Radeon AI PRO R9700 holds Qwen 3.8 27B.
Which is faster for local AI, the AMD Radeon AI PRO R9700 or the NVIDIA GeForce RTX 4070 Super?
On the models both run fully in memory, the AMD Radeon AI PRO R9700 is about 1.1× as fast as the NVIDIA GeForce RTX 4070 Super (estimated, median across models).
What is the price difference between the AMD Radeon AI PRO R9700 and the NVIDIA GeForce RTX 4070 Super?
In Germany the AMD Radeon AI PRO R9700 costs 2.390 € at eBay and the NVIDIA GeForce RTX 4070 Super 1.800 € at eBay: the NVIDIA GeForce RTX 4070 Super is 590 € cheaper.

More comparisons