readygpu

NVIDIA GeForce RTX 5080 vs NVIDIA GeForce RTX 5090

For running models locally, priced in Germany. At 64k context the first runs 26 models fully in memory, the second 49.

In short

The NVIDIA GeForce RTX 5090 has more memory for models: 32 GB against 16 GB. At 64k context the NVIDIA GeForce RTX 5090 runs 49 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 26; only the NVIDIA GeForce RTX 5090 holds Qwen 3.8 27B. On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 1.9× as fast as the NVIDIA GeForce RTX 5080 (estimated, median across models). In Germany the NVIDIA GeForce RTX 5080 costs 1.500 € at eBay and the NVIDIA GeForce RTX 5090 6.028 € at Amazon: the NVIDIA GeForce RTX 5080 is 4.528 € cheaper.

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

NVIDIA GeForce RTX 5080

1.500 €

eBay

Add to build
NVIDIA GeForce RTX 5090

6.028 €

Amazon

Add to build

Specifications

SpecNVIDIA GeForce RTX 5080NVIDIA GeForce RTX 5090
GPUGeForce RTX 5080GeForce RTX 5090
Memory16 GB GDDR732 GB GDDR7
Memory bus256-bit512-bit
Memory bandwidth960 GB/s1,792 GB/s
FP16 compute113 TFLOPS209 TFLOPS
SoftwareCUDACUDA
Board power360 W575 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 5080NVIDIA GeForce RTX 5090
Qwen 3.8 27Boffload39tok/sQ6_K
Qwen 3.6 27Boffload41tok/sQ6_K
Gemma 4 31Boffload35tok/sQ6_K
Qwen 3.6 35B-A3Boffload167tok/sQ6_K
Qwen 3.5 27Boffload41tok/sQ6_K
Gemma 4 26B-A4Boffload117tok/sQ8_0
Qwen 3.5 35B-A3Boffload175tok/sQ6_K
GLM 4.7 Flashoffload87tok/sQ6_K
Devstral Small 2 24Boffload37tok/sQ6_K
gpt-oss 20B88tok/sMXFP4165tok/sMXFP4
Kimi Linear 48B-A3Boffload277tok/sQ4_K_M
Qwen3 Coder 30B-A3Boffload75tok/sQ6_K
Gemma 4 12B42tok/sQ8_079tok/sQ8_0
Qwen 3.5 9B51tok/sQ8_095tok/sQ8_0
Gemma 3 27Boffload40tok/sQ6_K
Mistral Small 3.2 24Boffload37tok/sQ6_K
Ministral 3 14Boffload44tok/sQ8_0
Qwen3 14Boffload42tok/sQ8_0
DeepSeek R1 0528 Qwen3 8B41tok/sQ4_K_M61tok/sQ8_0
Qwen3 8B41tok/sQ4_K_M61tok/sQ8_0
Phi-4 14Boffload38tok/sQ8_0
Qwen 3.5 4B89tok/sQ8_0166tok/sQ8_0
Ministral 3 8B39tok/sQ5_K_M61tok/sQ8_0
Granite 4.2 8Boffload55tok/sQ8_0
Gemma 4 E4B59tok/sQ8_0110tok/sQ8_0
LFM2.5 8B-A1B83tok/sQ8_0156tok/sQ8_0
Llama 3.1 8B39tok/sQ6_K73tok/sQ6_K
Qwen2.5 0.5B445tok/sQ8_0831tok/sQ8_0
Qwen3.5 0.8B364tok/sQ8_0679tok/sQ8_0
Qwen3.5 2B263tok/sQ5_K_M492tok/sQ5_K_M
DeepSeek R1 Distill Qwen 1.5B158tok/sQ8_0294tok/sQ8_0
MiniCPM5 2B108tok/sQ8_0202tok/sQ8_0
Mellum2.1 12B A2.5B Thinking98tok/sQ8_0183tok/sQ8_0
LFM2.5 2.6B86tok/sQ8_0161tok/sQ8_0
LFM2.5 VL 3B86tok/sQ8_0161tok/sQ8_0
Kimi VL A3B85tok/smlx-5bit126tok/smlx-8bit
granite vision 4.1 4b66tok/sQ8_0124tok/sQ8_0
granite 4.2 3b64tok/sQ8_0120tok/sQ8_0
DeepSeek R1 Distill Qwen 7B50tok/sQ8_094tok/sQ8_0
GLM 4.6V Flash47tok/sQ8_088tok/sQ8_0
GLM 4.1V 9B Thinking41tok/smlx-8bit77tok/smlx-8bit
DeepSeek R1 Distill Llama 8B39tok/sQ6_K65tok/sQ8_0
Ministral 3 8B Reasoning 251239tok/sQ5_K_M61tok/sQ8_0
LFM2.5 24B A2Boffload89tok/sQ8_0
DeepSeek R1 Distill Qwen 14Boffload39tok/sQ8_0
Devstral Small 2507offload40tok/sQ5_K_M
Magistral Small 2506offload37tok/sQ6_K
Magistral Small 2507offload40tok/sQ5_K_M
Magistral Small 2509offload40tok/sQ5_K_M
Qwen 3.5 122B-A10Bwon't runoffload
Nemotron 3 Super 120B-A12Bwon't runoffload
Qwen3 Coder Nextwon't runoffload
Mistral Small 4 119Boffloadoffload
GLM 4.5 Airwon't runoffload
Qwen3 Next 80B-A3Bwon't runoffload
Nemotron 3.5 Lightning 30B-A3Boffloadoffload
Qwen3 32Boffloadoffload
DeepSeek R1 Distill Qwen 32Boffloadoffload
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
gpt-oss 120Bwon'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 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 NVIDIA GeForce RTX 5080 or the NVIDIA GeForce RTX 5090?
Choose the NVIDIA GeForce RTX 5090 to run bigger models. Choose the NVIDIA GeForce RTX 5090 for speed. Choose the NVIDIA GeForce RTX 5080 to spend less.
Which can run bigger models, the NVIDIA GeForce RTX 5080 or the NVIDIA GeForce RTX 5090?
At 64k context the NVIDIA GeForce RTX 5090 runs 49 of the models we track fully in memory and the NVIDIA GeForce RTX 5080 26; only the NVIDIA GeForce RTX 5090 holds Qwen 3.8 27B.
Which is faster for local AI, the NVIDIA GeForce RTX 5080 or the NVIDIA GeForce RTX 5090?
On the models both run fully in memory, the NVIDIA GeForce RTX 5090 is about 1.9× as fast as the NVIDIA GeForce RTX 5080 (estimated, median across models).
What is the price difference between the NVIDIA GeForce RTX 5080 and the NVIDIA GeForce RTX 5090?
In Germany the NVIDIA GeForce RTX 5080 costs 1.500 € at eBay and the NVIDIA GeForce RTX 5090 6.028 € at Amazon: the NVIDIA GeForce RTX 5080 is 4.528 € cheaper.

More comparisons