readygpu

AMD Radeon AI PRO R9700 vs NVIDIA GeForce RTX 5080

For running models locally, priced in Germany. At 32k context the first runs 52 models fully in memory, the second 30.

In short

The AMD Radeon AI PRO R9700 has more memory for models: 32 GB against 16 GB. At 32k context the AMD Radeon AI PRO R9700 runs 52 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 30; 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 27B11tok/sQ8_0offload
Qwen 3.6 27B11tok/sQ8_0offload
Gemma 4 31B12tok/sQ6_Koffload
Qwen 3.6 35B-A3B64tok/sQ6_Koffload
Qwen 3.5 27B11tok/sQ8_0offload
Gemma 4 26B-A4B42tok/sQ8_0offload
Qwen 3.5 35B-A3B67tok/sQ6_Koffload
GLM 4.7 Flash36tok/sQ6_Koffload
Devstral Small 2 24B12tok/sQ8_0offload
Kimi Linear 48B-A3B99tok/sQ4_K_Moffload
gpt-oss 20B65tok/sMXFP4110tok/sMXFP4
Qwen3 Coder 30B-A3B37tok/sQ6_Koffload
Qwen3 32B11tok/sQ5_K_Moffload
Gemma 4 12B26tok/sQ8_044tok/sQ8_0
Qwen 3.5 9B33tok/sQ8_056tok/sQ8_0
Mistral Small 3.2 24B12tok/sQ8_0offload
DeepSeek R1 Distill Qwen 32B11tok/sQ5_K_Moffload
Gemma 3 27B11tok/sQ8_0offload
Ministral 3 14B18tok/sQ8_040tok/sQ5_K_M
Qwen3 14B17tok/sQ8_041tok/sQ4_K_M
DeepSeek R1 0528 Qwen3 8B26tok/sQ8_044tok/sQ8_0
Qwen3 8B26tok/sQ8_044tok/sQ8_0
Phi-4 14B16tok/sQ8_0offload
Qwen 3.5 4B63tok/sQ8_0106tok/sQ8_0
Ministral 3 8B26tok/sQ8_044tok/sQ8_0
Granite 4.2 8B24tok/sQ8_041tok/sQ8_0
Gemma 4 E4B38tok/sQ8_065tok/sQ8_0
LFM2.5 8B-A1B79tok/sQ8_0134tok/sQ8_0
Llama 3.1 8B32tok/sQ6_K55tok/sQ6_K
Qwen2.5 0.5B377tok/sQ8_0637tok/sQ8_0
Qwen3.5 0.8B285tok/sQ8_0483tok/sQ8_0
Qwen3.5 2B190tok/sQ5_K_M321tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B124tok/sQ8_0210tok/sQ8_0
MiniCPM5 2B86tok/sQ8_0146tok/sQ8_0
LFM2.5 2.6B72tok/sQ8_0122tok/sQ8_0
LFM2.5 VL 3B72tok/sQ8_0122tok/sQ8_0
Mellum2.1 12B A2.5B Thinking67tok/sQ8_0113tok/sQ8_0
granite vision 4.1 4b56tok/sQ8_094tok/sQ8_0
granite 4.2 3b54tok/sQ8_091tok/sQ8_0
Kimi VL A3B49tok/smlx-8bit101tok/smlx-6bit
LFM2.5 24B A2B44tok/sQ8_0offload
DeepSeek R1 Distill Qwen 7B35tok/sQ8_060tok/sQ8_0
GLM 4.6V Flash31tok/sQ8_053tok/sQ8_0
DeepSeek R1 Distill Llama 8B27tok/sQ8_046tok/sQ8_0
GLM 4.1V 9B Thinking27tok/smlx-8bit45tok/smlx-8bit
Ministral 3 8B Reasoning 251226tok/sQ8_044tok/sQ8_0
DeepSeek R1 Distill Qwen 14B16tok/sQ8_039tok/sQ4_K_M
granite 4.2 30b12tok/sQ5_K_Moffload
Devstral Small 250712tok/sQ8_0offload
Magistral Small 250612tok/sQ8_0offload
Magistral Small 250712tok/sQ8_0offload
Magistral Small 250912tok/sQ8_0offload
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 32k context the AMD Radeon AI PRO R9700 runs 52 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 30; 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