readygpu

NVIDIA GeForce RTX 5080

16 GB · 960 GB/s · 360 W

In short

The NVIDIA GeForce RTX 5080 has 16 GB of GDDR7 memory with 960 GB/s of bandwidth, which sets how fast it generates text. At 128k context it runs 18 of the 113 open models we track fully in memory; the most capable is gpt-oss 20B at Q4_K_M, at about 64 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5080 in Germany is 1.500 € at eBay; used, it starts at 1.449 € (asking price).

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

Prices

Every retailer we track in Germany, cheapest first. Buy links may earn us a commission.

RetailerConditionPriceStockCheckedBuy
eBayINNO3D GeForce RTX 5080 X3 16GB GDDR7 Grafikkarte + Rechnungused, asking price1.449 €In stock2 h agoBuy
eBayGrafikkarte Zotac Gaming GeForce RTX 5080 SOLID Core OCNew1.500 €In stock2 h agoBuy
eBayPNY RTX 5080 Slim OC 16GB GDDR7 PCIE 5.0 x16 OVP + Rechnungused, asking price1.500 €+ 6 € deliveryIn stock2 h agoBuy
eBayMSI INSPIRE 3X BLACK GeForce RTX 5080 16GB GDDR7 OC GrafikkarteNew1.500 €+ 8 € deliveryIn stock2 h agoBuy
eBayASUS RTX 5080 PRIME OC EVO 16GB GDDR7 Nvidia Geforceused, asking price1.549 €In stock2 h agoBuy
AmazonPNY GeForce RTX 5080 16GB ARGB OC Triple Fan Graphics Card DLSS 4New1.597 €In stock34 min agoBuy
AmazonMSI GeForce RTX 5080 16G Ventus 3X OC Black Gaming Graphics CardNew1.599 €In stock34 min agoBuy
eBayMSI GeForce RTX 5080 INSPIRE 3X OC BLACK 16GB GDDR7 Grafikkarte Neuused, asking price1.609 €In stock2 h agoBuy
eBayZOTAC GeForce RTX 5080 AMP Extreme INFINITY 16GB GDDR7 GrafikkarteNew1.610 €+ 6 € deliveryIn stock2 h agoBuy
AmazonMSI GeForce RTX 5080 16G Ventus 3X OC Gaming Graphics CardNew1.629 €In stock13 h agoBuy
eBayPNY GeForce RTX 5080 Overclocked Triple FanNew1.639 €In stock2 h agoBuy
AmazonPNY GeForce RTX 5080 16GB Triple Fan Graphics Card DLSS 4New1.644 €In stock34 min agoBuy
AmazonPNY GeForce RTX 5080 16GB OC Triple Fan Graphics Card DLSS 4New1.639 €+ 5 € deliveryIn stock13 h agoBuy
AmazonGigabyte GeForce RTX 5080 WINDFORCE OC SFF 16G Graphics CardNew1.649 €In stock34 min agoBuy
AmazonGigabyte GeForce RTX 5080 Gaming OC 16G Graphics CardNew1.656 €In stock41 min agoBuy
AmazonPNY RTX5080 Verto ARGB OC Triple Fan 16GB GDDR7 HDMI 3xDPNew1.669 €In stock34 min agoBuy
eBayGigaByte GeForce RTX 5080 Windforce OC 16 GB GDDR7 256 BitNew1.682 €In stock2 h agoBuy
AmazonASUS Prime GeForce RTX 5080 OC Edition 16GB GDDR7 Gaming Graphics CardNew1.686 €In stock34 min agoBuy
eBay16GB Asus Nvidia GeForce RTX PRIME OC Edition GDDR7 Gaming Grafikkarte 5080used, asking price1.690 €+ 7 € deliveryIn stock2 h agoBuy
eBayMSI RTX 5080 Mandalorian & Grogu OC Refurbished 16GB Limited Edition 500 Stückused, asking price1.699 €In stock2 h agoBuy
eBayASUS Prime GeForce RTX 5080 OC Edition 16GB GDDR7 *NEU*New1.699 €In stock2 h agoBuy
AmazonPNY NVIDIA GeForce RTX 5080 Slim Dual Fan Dual Slot Graphics CardNew1.704 €In stock35 min agoBuy
eBayZotac GeForce RTX 5080 Solid Core OC 16 GB GDDR7 PCIe 5.0 x16New1.717 €In stock2 h agoBuy
AmazonGigabyte GeForce RTX 5080 WINDFORCE OC SFF 16GNew1.720 €In stock34 min agoBuy
AmazonMSI GeForce RTX 5080 16G Gaming Trio OCNew1.729 €In stock34 min agoBuy
AmazonASUS ProArt GeForce RTX 5080 16GB OC GDDR7 Content Creation Graphics CardNew1.745 €In stock34 min agoBuy
eBayASUS Prime GeForce RTX 5080 OC 16GB GDDR7 Gaming Grafikkarte PCIe 5.0New1.749 €In stock2 h agoBuy
AmazonMSI GeForce RTX 5080 16G Inspire 3X OC BlackNew1.761 €In stock34 min agoBuy
eBayASUS Prime GeForce RTX 5080 16GB GDDR7 Gaming GrafikkarteNew1.761 €In stock2 h agoBuy
eBayGigabyte GeForce Nvidia RTX 5080 AERO OC SFF 16GB GDDR7 HDMI 3x DP NEU ab LagerNew1.750 €+ 12 € deliveryIn stock2 h agoBuy
AmazonMSI GeForce RTX 5080 16G Shadow 3X OC Gaming Graphics CardNew1.849 €In stock34 min agoBuy
eBayGigabyte GeForce RTX 5080 Gaming OC 16G GrafikkarteNew1.850 €+ 8 € deliveryIn stock2 h agoBuy
eBayASUS ProArt GeForce RTX 5080 16GB OC Edition GDDR7 Content Creation GrafikkarteNew1.862 €In stock2 h agoBuy
eBayMSI GeForce RTX 5080 Suprim 16gb Rechnung Januar 2026 Deutscher Händlerused, asking price1.892 €In stock2 h agoBuy
eBayPNY GeForce RTX 5080 16GB ARGB OC Triple Fan Grafikkarte DLSS 4New1.900 €In stock2 h agoBuy
eBayPNY GeForce RTX 5080 ARGB Epic-X RGB Overclocked Triple FanNew1.901 €In stock2 h agoBuy
eBayASUS RTX 5080 ROG ASTRAL GAMING OCused, asking price1.899 €+ 8 € deliveryIn stock2 h agoBuy
eBayGigabyte RTX5080 AORUS Master ICE 16GB GDDR7 HDMI 3xDPused, asking price1.899 €+ 10 € deliveryIn stock2 h agoBuy
eBayNVIDIA GeForce RTX 5080 Founders Edition FE 16GB Grafikkarteused, asking price1.899 €+ 30 € deliveryIn stock2 h agoBuy
AmazonMSI GeForce RTX 5080 16G Gaming Trio OC WhiteNew1.960 €In stock34 min agoBuy
AmazonASUS ROG Astral GeForce RTX 5080 16GB GDDR7 OC Edition Gaming Graphics CardNew2.131 €In stock41 min agoBuy
eBayASUS ROG Astral GeForce RTX 5080 OC 16GB Hatsune Miku Edition neuwertig OVP NEUused, asking price3.499 €+ 10 € deliveryIn stock2 h agoBuy
eBayASUS TUF Gaming GeForce RTX 5080 OC Edition 16GB GDDR7used, asking price3.936 €+ 10 € deliveryIn stock2 h agoBuy

Used on eBay: median asking price 1.899 €, most between 1.774 € and 2.150 € (15 listings, 2026-10-15).

Price history

Lowest price shown each day over the last 90 days.

Not enough price history yet.

What it runs

Every model in the catalogue, with the best quant for this hardware. Estimates, not measurements.

ModelQuantFitsMemoryMax contextDecode @128kPrefillGood for
gpt-oss 20B

OpenAI

Q4_K_Mfits15.3 GB128k

64tok/sest.

2388 tok/schat, coding, agents, long documents
Gemma 4 12B

Google

Q6_Kfits12.9 GB245k256k with q8 cache

49tok/sest.

1533 tok/schat, coding, long documents
Qwen 3.5 9B

Alibaba Qwen

Q8_0fits14.4 GB155k256k with q8 cache

43tok/sest.

1823 tok/schat, coding, long documents
Qwen 3.5 4B

Alibaba Qwen

Q8_0fits9.7 GB256k

67tok/sest.

2839 tok/schat, coding, long documents
Gemma 4 E4B

Google

Q8_0fits12.6 GB128k

50tok/sest.

2556 tok/schat, coding, long documents
LFM2.5 8B-A1B

Liquid AI

UD-Q6_Kfits14.1 GB125k

49tok/sest.

3416 tok/schat, coding, long documents
Qwen2.5 0.5B

Alibaba Qwen

Q8_0fits3.4 GB32k

278tok/sest.

7675 tok/schat, coding, long documents
Qwen3.5 0.8B

Alibaba Qwen

Q8_0fits3.7 GB256k

244tok/sest.

10235 tok/schat, coding, agents, long documents
Qwen3.5 2B

Alibaba Qwen

Q5_K_Mfits4.3 GB256k

194tok/sest.

6545 tok/schat, coding, agents, long documents
DeepSeek R1 Distill Qwen 1.5B

DeepSeek

Q8_0fits6.7 GB128k

105tok/sest.

3429 tok/schat, coding, long documents
Mellum2.1 12B A2.5B Thinking

JetBrains

Q8_0fits15.3 GB128k

78tok/sest.

3952 tok/schat, coding, agents, long documents
MiniCPM5 2B

openbmb

Q8_0fits9.2 GB128k

72tok/sest.

1844 tok/schat, coding, agents, long documents
LFM2.5 2.6B

Liquid AI

Q8_0fits11.6 GB128k

55tok/sest.

2365 tok/schat, coding, agents, long documents
LFM2.5 VL 3B

Liquid AI

Q8_0fits11.6 GB32k

55tok/sest.

2275 tok/schat, coding, agents, long documents
GLM 4.6V Flash

Z.ai

Q4_K_Mfits12.2 GB128k

52tok/sest.

800 tok/schat, coding, agents, long documents
DeepSeek R1 Distill Qwen 7B

DeepSeek

Q6_Kfits14.3 GB128k

43tok/sest.

1224 tok/schat, coding, long documents
granite vision 4.1 4b

IBM

Q8_0fits14.8 GB128k

42tok/sest.

1460 tok/schat, coding, long documents
granite 4.2 3b

IBM

Q8_0fits15.1 GB128k

41tok/sest.

1489 tok/schat, coding, agents, long documents
Qwen 3.8 27B

Alibaba Qwen

UD-Q4_K_Moffload24.9 GB–

5tok/sest.

473 tok/schat
Qwen 3.6 27B

Alibaba Qwen

Q4_K_Moffload25.3 GB–

5tok/sest.

470 tok/schat
Gemma 4 31B

Google

Q4_K_Moffload29.3 GB–

3tok/sest.

416 tok/s–
Qwen 3.6 35B-A3B

Alibaba Qwen

MXFP4offload24.2 GB–

16tok/sest.

2332 tok/schat, coding, agents, long documents
Qwen 3.5 27B

Alibaba Qwen

Q4_K_Moffload25.2 GB–

5tok/sest.

471 tok/schat
Gemma 4 26B-A4B

Google

UD-Q4_K_Moffload19.9 GB–

19tok/sest.

3146 tok/schat, coding, agents, long documents
Qwen 3.5 35B-A3B

Alibaba Qwen

Q4_K_Moffload24.5 GB–

16tok/sest.

2318 tok/schat, coding, agents, long documents
GLM 4.7 Flash

Z.ai

Q4_K_Moffload25.1 GB–

7tok/sest.

1080 tok/schat, coding
Devstral Small 2 24B

Mistral AI

Q4_K_Moffload34.8 GB8k15k with q8 cache

2tok/sest.

364 tok/schat
Nemotron 3.5 Lightning 30B-A3B

NVIDIA

UD-Q6_K_XLoffload34.8 GB–

12tok/sest.

2659 tok/schat
Kimi Linear 48B-A3B

Moonshot AI

Q4_K_Moffload30.5 GB–

20tok/sest.

1569 tok/schat, coding, long documents
Qwen3 Coder 30B-A3B

Alibaba Qwen

Q4_K_Moffload30.7 GB–

4tok/sest.

606 tok/schat
Gemma 3 27B

Google

Q4_K_Moffload27.3 GB–

4tok/sest.

554 tok/schat
Mistral Small 3.2 24B

Mistral AI

Q4_K_Moffload34.8 GB8k15k with q8 cache

2tok/sest.

364 tok/schat
Ministral 3 14B

Mistral AI

Q4_K_Moffload29.1 GB43k79k with q8 cache

3tok/sest.

504 tok/schat, coding
Qwen3 14B

Alibaba Qwen

Q4_K_Moffload29.8 GB38k40k with q8 cache

3tok/sest.

425 tok/schat, coding
DeepSeek R1 0528 Qwen3 8B

DeepSeek

Q4_K_Moffload24.1 GB68k124k with q8 cache

5tok/sest.

711 tok/schat, coding
Qwen3 8B

Alibaba Qwen

Q4_K_Moffload24.1 GB40k

5tok/sest.

711 tok/schat, coding
Phi-4 14B

Microsoft

Q4_K_Moffload34.7 GB16k

2tok/sest.

399 tok/schat, coding
Ministral 3 8B

Mistral AI

Q4_K_Moffload23.3 GB71k129k with q8 cache

6tok/sest.

733 tok/schat, coding
Granite 4.2 8B

IBM

Q4_K_Moffload26.6 GB58k107k with q8 cache

4tok/sest.

616 tok/schat, coding, agents
Llama 3.1 8B

Meta

Q4_K_Moffload22.0 GB77k128k with q8 cache

6tok/sest.

814 tok/schat, coding
Kimi VL A3B

Moonshot AI

mlx-5bitoffload16.3 GB103k128k with q8 cache

36tok/sest.

2394 tok/schat, coding, agents, long documents
GLM 4.1V 9B Thinking

Z.ai

mlx-8bitoffload17.4 GB64k

15tok/sest.

740 tok/schat, coding, long documents
DeepSeek R1 Distill Llama 8B

DeepSeek

Q4_K_Moffload22.0 GB77k128k with q8 cache

6tok/sest.

814 tok/schat, coding
LFM2.5 24B A2B

Liquid AI

Q4_K_Moffload25.7 GB4k8k with q8 cache

6tok/sest.

1486 tok/schat, coding, agents
Ministral 3 8B Reasoning 2512

Mistral AI

Q4_K_Moffload23.3 GB71k129k with q8 cache

6tok/sest.

733 tok/schat, coding, agents
DeepSeek R1 Distill Qwen 14B

DeepSeek

Q4_K_Moffload33.8 GB32k60k with q8 cache

3tok/sest.

356 tok/schat, coding
Devstral Small 2507

Mistral AI

Q4_K_Moffload34.8 GB8k15k with q8 cache

2tok/sest.

367 tok/schat
Magistral Small 2506

Mistral AI

Q4_K_Moffload34.8 GB8k15k with q8 cache

2tok/sest.

367 tok/schat
Magistral Small 2507

Mistral AI

Q4_K_Moffload34.8 GB8k15k with q8 cache

2tok/sest.

367 tok/schat
Magistral Small 2509

Mistral AI

Q4_K_Moffload34.8 GB8k15k with q8 cache

2tok/sest.

364 tok/schat
DeepSeek V4 Flash

DeepSeek

UD-Q2_K_XLwon't run102.4 GB––––
GLM 5.3 Flash

Z.ai

UD-Q2_K_XLwon't run104.2 GB––––
Qwen 3.8 Flash Next

Alibaba Qwen

UD-Q2_K_XLwon't run78.0 GB––––
MiniMax M2.7

MiniMax

UD-Q2_K_XLwon't run102.6 GB––––
Qwen 3.5 122B-A10B

Alibaba Qwen

UD-Q2_K_XLwon't run43.6 GB––––
Nemotron 3 Super 120B-A12B

NVIDIA

UD-Q2_K_XLwon't run53.5 GB––––
Qwen3 Coder Next

Alibaba Qwen

Q4_K_Mwon't run49.7 GB––––
gpt-oss 120B

OpenAI

Q4_K_Mwon't run64.4 GB––––
Mistral Small 4 119B

Mistral AI

UD-Q2_K_XLwon't run41.7 GB––––
GLM 4.5 Air

Z.ai

Q2_Kwon't run66.7 GB––––
Qwen3 Next 80B-A3B

Alibaba Qwen

Q4_K_Mwon't run49.7 GB––––
Qwen3 32B

Alibaba Qwen

Q4_K_Mwon't run51.9 GB––––
DeepSeek R1 Distill Qwen 32B

DeepSeek

Q4_K_Mwon't run51.9 GB––––
Llama 3.3 70B

Meta

Q4_K_Mwon't run81.1 GB––––
DeepSeek R1

DeepSeek

Q4_K_Mwon't run386.7 GB––––
DeepSeek R1 0528

DeepSeek

Q4_K_Mwon't run387.2 GB––––
DeepSeek R1 Distill Llama 70B

DeepSeek

Q4_K_Mwon't run81.1 GB––––
DeepSeek V3 0324

DeepSeek

Q4_K_Mwon't run386.7 GB––––
DeepSeek V3.1

DeepSeek

Q4_K_Mwon't run387.6 GB––––
DeepSeek V3.2

DeepSeek

Q4_K_Mwon't run387.6 GB––––
DeepSeek V4 Flash 0731

DeepSeek

MXFP4won't run157.8 GB––––
DeepSeek V4 Flash Vision Exp

DeepSeek

MXFP4won't run166.6 GB––––
Devstral 2 123B Instruct 2512

Mistral AI

Q8_0won't run169.2 GB––––
GLM 4.5V

Z.ai

Q4_K_Mwon't run83.7 GB––––
GLM 4.6V

Z.ai

Q4_K_Mwon't run90.1 GB––––
GLM 4.7

Z.ai

Q4_K_Mwon't run249.0 GB––––
GLM 5.1

Z.ai

MXFP4won't run432.4 GB––––
GLM 5.2

Z.ai

UD-Q4_K_Mwon't run446.3 GB––––
GLM 5.3

Z.ai

Q8_0won't run758.7 GB––––
Kimi K2

Moonshot AI

Q4_K_Mwon't run588.2 GB––––
Kimi K2 Instruct 0905

Moonshot AI

Q4_K_Mwon't run588.6 GB––––
Kimi K2 Thinking

Moonshot AI

Q4_K_Mwon't run588.6 GB––––
Kimi K2.5

Moonshot AI

Q4_K_Mwon't run588.6 GB––––
MiniMax M2

MiniMax

Q4_K_Mwon't run161.3 GB––––
MiniMax M2.1

MiniMax

Q4_K_Mwon't run161.3 GB––––
MiniMax M2.5

MiniMax

MXFP4won't run147.7 GB––––
MiniMax M3

MiniMax

UD-Q4_K_Mwon't run263.2 GB––––
Mistral Medium 3.5 128B

Mistral AI

Q4_K_Mwon't run115.2 GB––––
granite 4.2 30b

IBM

Q4_K_Mwon't run50.2 GB––––

Specifications

From the manufacturer's published specifications; sources are linked where we have them.

GPU
GeForce RTX 5080
Memory
16 GB GDDR7
Memory bus
256-bit
Memory bandwidth
960 GB/s
FP16 compute
113 TFLOPS
Software
CUDA
Board power
360 W
PCIe generation
Gen 5
PCIe lanes
x16

Compare with

Questions

How much memory does the NVIDIA GeForce RTX 5080 have for AI models?
The NVIDIA GeForce RTX 5080 has 16 GB of GDDR7 memory with 960 GB/s of bandwidth, which sets how fast it generates text.
What is the best model the NVIDIA GeForce RTX 5080 can run locally?
gpt-oss 20B (Q4_K_M) fits fully in its memory at 128k context and generates at about 64 tok/s, an estimate from its memory bandwidth. 18 of the 113 models we track fit at that context.
Can the NVIDIA GeForce RTX 5080 run DeepSeek V4 Flash?
No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 102 GB at 128k context, more than the NVIDIA GeForce RTX 5080 and system RAM can hold.
How much does the NVIDIA GeForce RTX 5080 cost in Germany?
The best new price for the NVIDIA GeForce RTX 5080 in Germany is 1.500 € at eBay; used, it starts at 1.449 € (asking price).

Speeds on this page are for 128k context. See the best hardware for local AI at every budget.