readygpu

AMD Radeon AI PRO R9700 vs NVIDIA GeForce RTX 5080

For running models locally, priced in Germany. At 8k context the first runs 52 models fully in memory, the second 37.

In short

The AMD Radeon AI PRO R9700 has more memory for models: 32 GB against 16 GB. At 8k context the AMD Radeon AI PRO R9700 runs 52 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 37; only the AMD Radeon AI PRO R9700 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.7× as fast as the AMD Radeon AI PRO R9700 (estimated, median across models). In Germany the AMD Radeon AI PRO R9700 costs 1.867 € at Amazon and the NVIDIA GeForce RTX 5080 1.599 € at Amazon: the NVIDIA GeForce RTX 5080 is 268 € cheaper.

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

AMD Radeon AI PRO R9700

1.867 €

Amazon

Add to build
NVIDIA GeForce RTX 5080

1.599 €

Amazon

Add to build

Specifications

SpecAMD Radeon AI PRO R9700NVIDIA GeForce RTX 5080
GPURadeon AI PRO R9700GeForce RTX 5080
Memory32 GB GDDR616 GB GDDR7
Memory bus256-bit256-bit
Memory bandwidth640 GB/s960 GB/s
FP16 compute191 TFLOPS113 TFLOPS
SoftwareROCmCUDA
Board power300 W360 W
PCIe generationGen 5Gen 5
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 5080
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_038tok/sQ4_K_M
Kimi Linear 48B-A3B109tok/sQ4_K_Moffload
gpt-oss 20B80tok/sMXFP4136tok/sMXFP4
Qwen3 Coder 30B-A3B65tok/sQ6_Koffload
Qwen3 32B12tok/sQ6_Koffload
Gemma 4 12B27tok/sQ8_045tok/sQ8_0
Qwen 3.5 9B36tok/sQ8_060tok/sQ8_0
Mistral Small 3.2 24B13tok/sQ8_038tok/sQ4_K_M
DeepSeek R1 Distill Qwen 32B12tok/sQ6_Koffload
Gemma 3 27B12tok/sQ8_0offload
Ministral 3 14B22tok/sQ8_038tok/sQ8_0
Qwen3 14B21tok/sQ8_044tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B36tok/sQ8_060tok/sQ8_0
Qwen3 8B36tok/sQ8_060tok/sQ8_0
Phi-4 14B20tok/sQ8_043tok/sQ6_K
Qwen 3.5 4B73tok/sQ8_0124tok/sQ8_0
Ministral 3 8B35tok/sQ8_059tok/sQ8_0
Granite 4.2 8B33tok/sQ8_056tok/sQ8_0
Gemma 4 E4B42tok/sQ8_070tok/sQ8_0
LFM2.5 8B-A1B144tok/sQ8_0244tok/sQ8_0
Llama 3.1 8B46tok/sQ6_K78tok/sQ6_K
Qwen2.5 0.5B557tok/sQ8_0942tok/sQ8_0
Qwen3.5 0.8B378tok/sQ8_0639tok/sQ8_0
Qwen3.5 2B226tok/sQ5_K_M383tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B165tok/sQ8_0280tok/sQ8_0
MiniCPM5 2B116tok/sQ8_0196tok/sQ8_0
LFM2.5 2.6B104tok/sQ8_0176tok/sQ8_0
LFM2.5 VL 3B104tok/sQ8_0176tok/sQ8_0
granite vision 4.1 4b82tok/sQ8_0139tok/sQ8_0
granite 4.2 3b77tok/sQ8_0130tok/sQ8_0
LFM2.5 24B A2B76tok/sQ8_0offload
Mellum2.1 12B A2.5B Thinking75tok/sQ8_0127tok/sQ8_0
Kimi VL A3B60tok/smlx-8bit128tok/smlx-6bit
DeepSeek R1 Distill Qwen 7B41tok/sQ8_070tok/sQ8_0
DeepSeek R1 Distill Llama 8B37tok/sQ8_062tok/sQ8_0
Ministral 3 8B Reasoning 251235tok/sQ8_059tok/sQ8_0
GLM 4.6V Flash34tok/sQ8_058tok/sQ8_0
GLM 4.1V 9B Thinking29tok/smlx-8bit49tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B20tok/sQ8_043tok/sQ6_K
Devstral Small 250713tok/sQ8_038tok/sQ4_K_M
Magistral Small 250613tok/sQ8_038tok/sQ4_K_M
Magistral Small 250713tok/sQ8_038tok/sQ4_K_M
Magistral Small 250913tok/sQ8_038tok/sQ4_K_M
granite 4.2 30b13tok/sQ6_Koffload
Qwen 3.5 122B-A10Boffloadoffload
Qwen3 Coder Nextoffloadwon't run
Nemotron 3 Super 120B-A12Boffloadwon't run
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airoffloadwon't run
Qwen3 Next 80B-A3Boffloadwon't run
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
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 V3 0324won't runwon't run
DeepSeek V3.1won'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 4.6Vwon'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 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 5080?
Choose the AMD Radeon AI PRO R9700 to run bigger models. Choose the NVIDIA GeForce RTX 5080 for speed. Choose the NVIDIA GeForce RTX 5080 to spend less.
Which can run bigger models, the AMD Radeon AI PRO R9700 or the NVIDIA GeForce RTX 5080?
At 8k context the AMD Radeon AI PRO R9700 runs 52 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 37; 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 5080?
On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.7× as fast as the AMD Radeon AI PRO R9700 (estimated, median across models).
What is the price difference between the AMD Radeon AI PRO R9700 and the NVIDIA GeForce RTX 5080?
In Germany the AMD Radeon AI PRO R9700 costs 1.867 € at Amazon and the NVIDIA GeForce RTX 5080 1.599 € at Amazon: the NVIDIA GeForce RTX 5080 is 268 € cheaper.

More comparisons