readygpu

NVIDIA GeForce RTX 5060

8 GB · 448 GB/s · 145 W

In short

The NVIDIA GeForce RTX 5060 has 8 GB of GDDR7 memory with 448 GB/s of bandwidth, which sets how fast it generates text. At 64k context it runs 27 of the 129 open models we track fully in memory; the most capable is gpt-oss 20B at MXFP4, at about 41 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5060 in Germany is 449 € at eBay; used, it starts at 414 € (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
eBayPalit GeForce RTX 5060 Infinity 2 OC 8GB GDDR7 Grafikkarteused, asking price414 €+ 6 € deliveryIn stock35 min agoBuy
eBayUsed GeForce RTX 5060 on eBayused, asking price455 €In stock22 min agoBuy
eBayGigabyteused, asking price447 €+ 8 € deliveryIn stock35 min agoBuy
eBayINNO3D GeForce RTX 5060 Twin X2 8GB GDDR7 PCIe 5.0 x16 Grafikkarte NeuNew449 €+ 6 € deliveryIn stock35 min agoBuy
eBayASUS Dual GeForce RTX 5060 OC 8GB GDDR7 Grafikkarte PCIe 5.0used, asking price450 €+ 8 € deliveryIn stock35 min agoBuy
AmazonASUS Dual GeForce RTX 5060 8GB OC Edition GDDR7 Gaming Graphics CardNew485 €In stock4 h agoBuy
AmazonASUS Dual GeForce RTX 5060 8GB GDDR7 White OC Edition Gaming Graphics CardNew490 €In stock4 h agoBuy
eBayASUS Dual GeForce RTX 5060 OC 8GB GDDR7 DUAL-RTX5060-O8G Grafikkarte NEU OVPNew494 €In stock35 min agoBuy
AmazonASUS Dual GeForce RTX 5060 8GB GDDR7 OC Ed. Advanced Gaming Graphics CardNew499 €In stock4 h agoBuy
AmazonGigabyte GeForce RTX 5060 WINDFORCE OC 8G Graphics CardNew499 €In stock10 h agoBuy
eBayGIGABYTE GeForce RTX 5060 Windforce OC 8GNew500 €+ 7 € deliveryIn stock35 min agoBuy
eBayMSI GeForce Nvidia RTX 5060 VENTUS 2X OC Plus 8GB GDDR7 1xHDMI 3xDP Neu OVPNew500 €+ 9 € deliveryIn stock35 min agoBuy
eBayASUS TUF Gaming GeForce RTX 5060 OC 8GB GDDR7 Grafikkarte PCIe 5.0. Neu & OVP ✅✅New515 €In stock35 min agoBuy
AmazonGigabyte GeForce RTX 5060 WINDFORCE MAX OC V2 8GNew519 €In stock5 h agoBuy
eBayASUS PRIME-RTX5060-O8G NVIDIA Grafikkarteused, asking price522 €In stock35 min agoBuy
eBayASUS PRIME-RTX5060-O8G NVIDIA Grafikkarteused, asking price527 €In stock35 min agoBuy
AmazonGigabyte GeForce RTX 5060 WINDFORCE MAX OC 8G Graphics CardNew529 €In stock5 h agoBuy
AmazonASUS TUF Gaming GeForce RTX 5060 OC Edition 8GB GDDR7 Gaming Graphics CardNew529 €In stock4 h agoBuy
eBayGrafikkarte Palit GeForce RTX 5060 Infinity 2 OC 8GB GDDR7 Reflex 2 RTX AI DLSS4New530 €+ 6 € deliveryIn stock35 min agoBuy
eBayGrafikkarte MSI GeForce RTX 5060 Ventus 2X OC 8GB GDDR7 HDMI DisplayPort GamingNew530 €+ 7 € deliveryIn stock35 min agoBuy
AmazonMSI RTX5060 Ventus 2X OC V1 8GB GDDR7 HDMI 3xDPNew539 €In stock4 h agoBuy
eBayASUS GeForce RTX 5060 Dual OC 8GB GDDR7 DLSS4New546 €In stock35 min agoBuy
eBayGigaByte GeForce RTX 5060 Windforce Max OC 8 GB GDDR7 128 Bit 28 Gbit/sNew546 €In stock35 min agoBuy
eBayASUS PRIME-RTX5060-O8G NVIDIA GrafikkarteNew549 €In stock35 min agoBuy
eBayGigabyte GeForce RTX 5060 WINDFORCE OC 8GB GDDR7 PCIe 5.0 3xDP HDMINew550 €In stock35 min agoBuy
eBayASUS Dual GeForce RTX 5060 8GB GDDR7 OC Edition Advanced Gaming GrafikkarteNew551 €In stock35 min agoBuy
eBayGIGABYTE GeForce RTX 5060 OC Low Profile 8GB GDDR7 PCIe 5.0 DP/HDMIused, asking price549 €+ 6 € deliveryIn stock35 min agoBuy
AmazonGIGABYTE AORUS GeForce RTX 5060 ARI 8G Graphics CardNew589 €In stock4 h agoBuy
eBayZOTAC GAMING GeForce RTX 5060 Low Profile 8GB GDDR7 PCIe x16 HDMI/DPused, asking price600 €+ 6 € deliveryIn stock35 min agoBuy
AmazonASUS GeForce RTX 5060 LP BRK 8GB OC Edition Low Profile Gaming GraphicsNew682 €+ 5 € deliveryIn stock4 h agoBuy
eBayASUS Prime NVIDIA GeForce RTX 5060 8 GB + 64 GB Kingston Fury Beast DDR5 RAMused, asking price1.450 €+ 8 € deliveryIn stock35 min agoBuy

Used on eBay: median asking price 455 €, most between 448 € and 527 € (6 listings, 2026-11-04). Used price history

Price history

Lowest price shown each day over the last 90 days.

402 €432 €462 €2026-11-032026-11-04
Lowest new priceLowest used asking price

What two of them run

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

ModelQuantFitsMemoryMax contextDecode @64kPrefillGood for
gpt-oss 20B

OpenAI

MXFP4fits14.3 GB82k128k with q8 cache

41tok/sest.

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

Google

Q8_0fits14.6 GB73k122k with q8 cache

20tok/sest.

299 tok/schat, coding
Qwen 3.5 9B

Alibaba Qwen

Q8_0fits12.4 GB128k212k with q8 cache

24tok/sest.

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

Alibaba Qwen

Q8_0fits7.7 GB255k256k with q8 cache

42tok/sest.

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

Google

Q8_0fits10.9 GB128k

28tok/sest.

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

Liquid AI

Q8_0fits12.9 GB100k125k with q8 cache

39tok/sest.

1022 tok/schat, coding, long documents
Llama 3.1 8B

Meta

Q4_K_Mfits14.1 GB69k126k with q8 cache

21tok/sest.

260 tok/schat, coding
Qwen2.5 0.5B

Alibaba Qwen

Q8_0fits2.7 GB32k

208tok/sest.

2267 tok/schat, coding, long documents
Qwen3.5 0.8B

Alibaba Qwen

Q8_0fits3.0 GB256k

170tok/sest.

2570 tok/schat, coding, agents, long documents
Qwen3.5 2B

Alibaba Qwen

Q5_K_Mfits3.6 GB256k

123tok/sest.

1401 tok/schat, coding, agents, long documents
LFM3 1.7B

Liquid AI

Q8_0fits4.0 GB256k

104tok/sest.

1690 tok/schat, coding, agents, long documents
DeepSeek R1 Distill Qwen 1.5B

DeepSeek

Q8_0fits5.0 GB128k

74tok/sest.

939 tok/schat, coding, long documents
MiniCPM5 2B

openbmb

Q8_0fits6.6 GB128k

51tok/sest.

529 tok/schat, coding, agents, long documents
Spark X2.5 4B

XHToken

mlx-4bitfits6.6 GB263k441k with q8 cache

50tok/sest.

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

JetBrains

Q8_0fits14.4 GB83k125k with q8 cache

46tok/sest.

947 tok/schat, coding, agents, long documents
Kimi VL A3B Thinking 2506

Moonshot AI

Q4_K_Mfits13.2 GB109k128k with q8 cache

42tok/sest.

651 tok/schat, coding, long documents
FrogNano 4B 2609

Microsoft

Q8_0fits7.8 GB251k256k with q8 cache

41tok/sest.

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

Liquid AI

Q8_0fits7.9 GB128k

40tok/sest.

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

Liquid AI

Q8_0fits7.9 GB32k

40tok/sest.

604 tok/schat, coding, agents, long documents
Kimi VL A3B

Moonshot AI

mlx-5bitfits14.4 GB75k123k with q8 cache

40tok/sest.

512 tok/schat, coding, agents
granite vision 4.1 4b

IBM

Q8_0fits9.8 GB122k128k with q8 cache

31tok/sest.

403 tok/schat, coding
granite 4.2 3b

IBM

Q8_0fits10.1 GB119k128k with q8 cache

30tok/sest.

416 tok/schat, coding, agents
Ministral 3 3B Instruct 2512

Mistral AI

Q8_0fits11.4 GB95k172k with q8 cache

26tok/sest.

399 tok/schat, coding, agents
GLM 4 9B 0414

Z.ai

mlx-5bitfits11.7 GB32k

25tok/sest.

214 tok/schat, coding
DeepSeek R1 Distill Qwen 7B

DeepSeek

Q8_0fits12.5 GB101k128k with q8 cache

23tok/sest.

304 tok/schat, coding
GLM 4.6V Flash

Z.ai

Q8_0fits13.3 GB97k128k with q8 cache

22tok/sest.

205 tok/schat, coding
DeepSeek R1 Distill Llama 8B

DeepSeek

Q4_K_Mfits14.1 GB69k126k with q8 cache

21tok/sest.

260 tok/schat, coding
Qwen 3.8 27B

Alibaba Qwen

UD-Q4_K_Moffload20.9 GB–

6tok/sest.

102 tok/s–
Qwen 3.6 27B

Alibaba Qwen

Q4_K_Moffload21.3 GB–

6tok/sest.

101 tok/s–
Gemma 4 31B

Google

Q4_K_Moffload24.3 GB–

4tok/sest.

86 tok/s–
Mistral Small 4 119B

Mistral AI

UD-Q2_K_XLoffload40.3 GB–

12tok/sest.

156 tok/schat
Qwen 3.6 35B-A3B

Alibaba Qwen

MXFP4offload23.0 GB–

20tok/sest.

586 tok/schat, coding
Qwen 3.5 27B

Alibaba Qwen

Q4_K_Moffload21.2 GB–

6tok/sest.

102 tok/s–
Gemma 4 26B-A4B

Google

MXFP4offload18.3 GB–

22tok/sest.

679 tok/schat, coding
Qwen 3.5 35B-A3B

Alibaba Qwen

Q4_K_Moffload23.3 GB–

20tok/sest.

582 tok/schat, coding
GLM 4.7 Flash

Z.ai

Q4_K_Moffload21.8 GB–

10tok/sest.

299 tok/schat
Devstral Small 2 24B

Mistral AI

Q4_K_Moffload24.8 GB2k3k with q8 cache

4tok/sest.

92 tok/s–
Nemotron 3.5 Lightning 30B-A3B

NVIDIA

MXFP4offload23.5 GB–

24tok/sest.

714 tok/schat, coding, long documents
Kimi Linear 48B-A3B

Moonshot AI

Q4_K_Moffload30.0 GB–

22tok/sest.

415 tok/schat, coding
Qwen3 Coder 30B-A3B

Alibaba Qwen

Q4_K_Moffload24.8 GB–

7tok/sest.

202 tok/schat
Qwen3 32B

Alibaba Qwen

Q4_K_Moffload35.9 GB–

2tok/sest.

41 tok/s–
Gemma 3 27B

Google

Q4_K_Moffload22.3 GB–

5tok/sest.

111 tok/s–
Mistral Small 3.2 24B

Mistral AI

Q4_K_Moffload24.8 GB2k3k with q8 cache

4tok/sest.

92 tok/s–
DeepSeek R1 Distill Qwen 32B

DeepSeek

Q4_K_Moffload36.0 GB–

2tok/sest.

50 tok/s–
Ministral 3 14B

Mistral AI

Q4_K_Moffload19.1 GB37k67k with q8 cache

7tok/sest.

149 tok/schat, coding
Qwen3 14B

Alibaba Qwen

Q4_K_Moffload19.9 GB32k40k with q8 cache

7tok/sest.

128 tok/schat
DeepSeek R1 0528 Qwen3 8B

DeepSeek

Q4_K_Moffload15.2 GB61k111k with q8 cache

17tok/sest.

238 tok/schat, coding
Qwen3 8B

Alibaba Qwen

Q4_K_Moffload15.2 GB40k

17tok/sest.

238 tok/schat, coding
Phi-4 14B

Microsoft

Q4_K_Moffload22.3 GB16k

5tok/sest.

121 tok/schat
Ministral 3 8B

Mistral AI

Q4_K_Moffload14.8 GB63k115k with q8 cache

19tok/sest.

239 tok/schat, coding
Granite 4.2 8B

IBM

Q4_K_Moffload16.6 GB52k96k with q8 cache

11tok/sest.

205 tok/schat, coding
Ministral 3 8B Reasoning 2512

Mistral AI

Q4_K_Moffload14.8 GB63k115k with q8 cache

19tok/sest.

239 tok/schat, coding
GLM 4.1V 9B Thinking

Z.ai

mlx-8bitoffload14.9 GB60k64k with q8 cache

18tok/sest.

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

Liquid AI

Q4_K_Moffload20.8 GB–

11tok/sest.

477 tok/schat, coding
Muse Glimmer 30B

meta-models

Q4_K_Moffload18.5 GB–

8tok/sest.

111 tok/s–
Ministral 3 14B Reasoning 2512

Mistral AI

Q4_K_Moffload19.1 GB37k67k with q8 cache

7tok/sest.

149 tok/schat, coding
DeepSeek R1 Distill Qwen 14B

DeepSeek

Q4_K_Moffload21.8 GB27k50k with q8 cache

5tok/sest.

111 tok/schat
Devstral Small 2507

Mistral AI

Q4_K_Moffload24.8 GB2k3k with q8 cache

4tok/sest.

93 tok/s–
Magistral Small 2506

Mistral AI

Q4_K_Moffload24.8 GB2k3k with q8 cache

4tok/sest.

93 tok/s–
Magistral Small 2507

Mistral AI

Q4_K_Moffload24.8 GB2k3k with q8 cache

4tok/sest.

93 tok/s–
Magistral Small 2509

Mistral AI

Q4_K_Moffload24.8 GB2k3k with q8 cache

4tok/sest.

92 tok/s–
Qwen3.8 27B OBLITERATED

OBLITERATUS

mlx-4bitoffload24.9 GB–

4tok/sest.

94 tok/s–
granite 4.2 30b

IBM

Q4_K_Moffload34.3 GB–

2tok/sest.

60 tok/s–
DeepSeek V4 Flash

DeepSeek

UD-Q2_K_XLwon't run97.0 GB––––
GLM 5.3 Flash

Z.ai

UD-Q2_K_XLwon't run103.5 GB––––
Qwen 3.8 Flash Next

Alibaba Qwen

UD-Q2_K_XLwon't run76.5 GB––––
MiniMax M2.7

MiniMax

UD-Q2_K_XLwon't run87.1 GB––––
Qwen 3.5 122B-A10B

Alibaba Qwen

UD-Q2_K_XLwon't run42.1 GB––––
Nemotron 3 Super 120B-A12B

NVIDIA

UD-Q2_K_XLwon't run53.0 GB––––
Qwen3 Coder Next

Alibaba Qwen

Q4_K_Mwon't run48.2 GB––––
gpt-oss 120B

OpenAI

Q4_K_Mwon't run62.2 GB––––
GLM 4.5 Air

Z.ai

Q2_Kwon't run55.2 GB––––
Qwen3 Next 80B-A3B

Alibaba Qwen

Q4_K_Mwon't run48.2 GB––––
Llama 3.3 70B

Meta

Q4_K_Mwon't run61.1 GB––––
DeepSeek R1

DeepSeek

Q4_K_Mwon't run382.4 GB––––
DeepSeek R1 0528

DeepSeek

Q4_K_Mwon't run382.9 GB––––
DeepSeek R1 Distill Llama 70B

DeepSeek

Q4_K_Mwon't run61.1 GB––––
DeepSeek R1 Zero

DeepSeek

Q4_K_Mwon't run382.4 GB––––
DeepSeek V3

DeepSeek

Q4_K_Mwon't run382.4 GB––––
DeepSeek V3 0324

DeepSeek

Q4_K_Mwon't run382.4 GB––––
DeepSeek V3.1

DeepSeek

Q4_K_Mwon't run383.3 GB––––
DeepSeek V3.1 Terminus

DeepSeek

Q4_K_Mwon't run383.3 GB––––
DeepSeek V3.2

DeepSeek

Q4_K_Mwon't run383.3 GB––––
DeepSeek V4 Flash 0731

DeepSeek

MXFP4won't run152.5 GB––––
DeepSeek V4 Flash Vision Exp

DeepSeek

MXFP4won't run161.3 GB––––
Devstral 2 123B Instruct 2512

Mistral AI

Q4_K_Mwon't run93.2 GB––––
GLM 4.5

Z.ai

Q4_K_Mwon't run226.1 GB––––
GLM 4.5V

Z.ai

Q4_K_Mwon't run72.2 GB––––
GLM 4.6

Z.ai

Q4_K_Mwon't run225.3 GB––––
GLM 4.6V

Z.ai

Q4_K_Mwon't run78.6 GB––––
GLM 4.7

Z.ai

Q4_K_Mwon't run226.1 GB––––
GLM 5

Z.ai

MXFP4won't run389.3 GB––––
GLM 5.1

Z.ai

MXFP4won't run426.9 GB––––
GLM 5.2

Z.ai

UD-Q4_K_Mwon't run440.8 GB––––
GLM 5.3

Z.ai

Q8_0won't run753.3 GB––––
Kimi Dev 72B

Moonshot AI

Q6_Kwon't run81.4 GB––––
Kimi K2

Moonshot AI

Q4_K_Mwon't run583.9 GB––––
Kimi K2 Instruct 0905

Moonshot AI

Q4_K_Mwon't run584.3 GB––––
Kimi K2 Thinking

Moonshot AI

Q4_K_Mwon't run584.3 GB––––
Kimi K2.5

Moonshot AI

Q4_K_Mwon't run584.3 GB––––
MiniMax M2

MiniMax

Q4_K_Mwon't run145.8 GB––––
MiniMax M2.1

MiniMax

Q4_K_Mwon't run145.8 GB––––
MiniMax M2.5

MiniMax

MXFP4won't run132.2 GB––––
MiniMax M3

MiniMax

MXFP4won't run248.7 GB––––
Mistral Medium 3.5 128B

Mistral AI

Q4_K_Mwon't run93.2 GB––––

Specifications

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

GPU
GeForce RTX 5060
Memory
8 GB GDDR7
Memory bus
128-bit
Memory bandwidth
448 GB/s
FP16 compute
19.177 TFLOPS
Software
CUDA
Board power
145 W
PCIe generation
Gen 5
PCIe lanes
x8

Compare with

Questions

How much memory does the NVIDIA GeForce RTX 5060 have for AI models?
The NVIDIA GeForce RTX 5060 has 8 GB of GDDR7 memory with 448 GB/s of bandwidth, which sets how fast it generates text.
What is the best model the NVIDIA GeForce RTX 5060 can run locally?
gpt-oss 20B (MXFP4) fits fully in its memory at 64k context and generates at about 41 tok/s, an estimate from its memory bandwidth. 27 of the 129 models we track fit at that context.
Can the NVIDIA GeForce RTX 5060 run DeepSeek V4 Flash?
No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 97 GB at 64k context, more than the NVIDIA GeForce RTX 5060 and system RAM can hold.
How much does the NVIDIA GeForce RTX 5060 cost in Germany?
The best new price for the NVIDIA GeForce RTX 5060 in Germany is 449 € at eBay; used, it starts at 414 € (asking price).

Speeds on this page are for 64k context. See the best hardware for local AI at every budget.

More hardware for local AI