readygpu

NVIDIA GeForce RTX 5080 vs AMD Radeon RX 9070 XT

For running models locally, priced in Germany. At 8k context the first runs 39 models fully in memory, the second 33.

In short

Both have 16 GB of memory for models; the NVIDIA GeForce RTX 5080 has 960 GB/s of bandwidth and the AMD Radeon RX 9070 XT 640 GB/s. At 8k context the NVIDIA GeForce RTX 5080 runs 39 of the models we track fully in memory and the AMD Radeon RX 9070 XT 33; only the NVIDIA GeForce RTX 5080 holds Devstral Small 2 24B. On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.7× as fast as the AMD Radeon RX 9070 XT (estimated, median across models). In Germany the NVIDIA GeForce RTX 5080 costs 1.500 € at eBay and the AMD Radeon RX 9070 XT 789 € at eBay: the AMD Radeon RX 9070 XT is 711 € cheaper.

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

NVIDIA GeForce RTX 5080

1.500 €

eBay

Add to build
AMD Radeon RX 9070 XT

789 €

eBay

Add to build

Specifications

SpecNVIDIA GeForce RTX 5080AMD Radeon RX 9070 XT
GPUGeForce RTX 5080Radeon RX 9070 XT
Memory16 GB GDDR716 GB GDDR6
Memory bus256-bit256-bit
Memory bandwidth960 GB/s640 GB/s
FP16 compute113 TFLOPS195 TFLOPS
SoftwareCUDAROCm
Board power360 W304 W
PCIe generationGen 5Gen 5
PCIe lanesx16x16

What each runs

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

ModelNVIDIA GeForce RTX 5080AMD Radeon RX 9070 XT
Devstral Small 2 24B38tok/sQ4_K_Moffload
gpt-oss 20B136tok/sMXFP480tok/sMXFP4
Gemma 4 12B45tok/sQ8_027tok/sQ8_0
Qwen 3.5 9B60tok/sQ8_036tok/sQ8_0
Mistral Small 3.2 24B38tok/sQ4_K_Moffload
Qwen3 14B44tok/sQ6_K26tok/sQ6_K
Ministral 3 14B38tok/sQ8_028tok/sQ6_K
DeepSeek R1 0528 Qwen3 8B60tok/sQ8_036tok/sQ8_0
Qwen3 8B60tok/sQ8_036tok/sQ8_0
Phi-4 14B43tok/sQ6_K26tok/sQ6_K
Qwen 3.5 4B124tok/sQ8_073tok/sQ8_0
Ministral 3 8B59tok/sQ8_035tok/sQ8_0
Granite 4.2 8B56tok/sQ8_033tok/sQ8_0
Gemma 4 E4B70tok/sQ8_042tok/sQ8_0
LFM2.5 8B-A1B244tok/sQ8_0144tok/sQ8_0
Llama 3.1 8B78tok/sQ6_K46tok/sQ6_K
Qwen2.5 0.5B942tok/sQ8_0557tok/sQ8_0
Qwen3.5 0.8B639tok/sQ8_0378tok/sQ8_0
Qwen3.5 2B383tok/sQ5_K_M226tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B280tok/sQ8_0165tok/sQ8_0
MiniCPM5 2B196tok/sQ8_0116tok/sQ8_0
LFM2.5 2.6B176tok/sQ8_0104tok/sQ8_0
LFM2.5 VL 3B176tok/sQ8_0104tok/sQ8_0
Kimi VL A3B Thinking 2506164tok/sQ4_K_M97tok/sQ4_K_M
granite vision 4.1 4b139tok/sQ8_082tok/sQ8_0
granite 4.2 3b130tok/sQ8_077tok/sQ8_0
Kimi VL A3B128tok/smlx-6bit76tok/smlx-6bit
Mellum2.1 12B A2.5B Thinking127tok/sQ8_075tok/sQ8_0
DeepSeek R1 Distill Qwen 7B70tok/sQ8_041tok/sQ8_0
GLM 4 9B 041469tok/smlx-5bit41tok/smlx-5bit
DeepSeek R1 Distill Llama 8B62tok/sQ8_037tok/sQ8_0
Ministral 3 8B Reasoning 251259tok/sQ8_035tok/sQ8_0
GLM 4.6V Flash58tok/sQ8_034tok/sQ8_0
GLM 4.1V 9B Thinking49tok/smlx-8bit29tok/smlx-8bit
DeepSeek R1 Distill Qwen 14B43tok/sQ6_K26tok/sQ6_K
Devstral Small 250738tok/sQ4_K_Moffload
Magistral Small 250638tok/sQ4_K_Moffload
Magistral Small 250738tok/sQ4_K_Moffload
Magistral Small 250938tok/sQ4_K_Moffload
Qwen 3.8 27Boffloadoffload
Qwen 3.5 122B-A10Boffloadoffload
Qwen 3.6 27Boffloadoffload
Gemma 4 31Boffloadoffload
Mistral Small 4 119Boffloadoffload
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
LFM2.5 24B A2Boffloadoffload
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 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 4.5Vwon'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 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 5080 or the AMD Radeon RX 9070 XT?
Choose the NVIDIA GeForce RTX 5080 to run bigger models. Choose the NVIDIA GeForce RTX 5080 for speed. Choose the AMD Radeon RX 9070 XT to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 5080 or the AMD Radeon RX 9070 XT?
At 8k context the NVIDIA GeForce RTX 5080 runs 39 of the models we track fully in memory and the AMD Radeon RX 9070 XT 33; only the NVIDIA GeForce RTX 5080 holds Devstral Small 2 24B.
Which is faster for local AI, the NVIDIA GeForce RTX 5080 or the AMD Radeon RX 9070 XT?
On the models both run fully in memory, the NVIDIA GeForce RTX 5080 is about 1.7× as fast as the AMD Radeon RX 9070 XT (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 5080 and the AMD Radeon RX 9070 XT?
In Germany the NVIDIA GeForce RTX 5080 costs 1.500 € at eBay and the AMD Radeon RX 9070 XT 789 € at eBay: the AMD Radeon RX 9070 XT is 711 € cheaper.

More comparisons

NVIDIA GeForce RTX 5080 vs AMD Radeon RX 9070 XT for local AI (DE) · readygpu