readygpu

NVIDIA GeForce RTX 5060 Ti 8GB

8 GB · 448 GB/s · 180 W

In short

The NVIDIA GeForce RTX 5060 Ti 8GB has 8 GB of GDDR7 memory with 448 GB/s of bandwidth, which sets how fast it generates text. At 32k context it runs 18 of the 129 open models we track fully in memory; the most capable is Qwen 3.5 9B at Q4_K_M, at about 41 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5060 Ti 8GB in Germany is 518 € at eBay; used, it starts at 529 € (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
eBayMSI GeForce RTX 5060 Ti 8G Ventus 2X OC PlusNew518 €In stock2 h agoBuy
AmazonPNY Geforce RTX 5060 Ti 8GB Overclocked Dual Fan DLSS 4New525 €In stock9 h agoBuy
eBayMSI GeForce RTX 5060 Ti GAMING TRIO OC Grafikkarte 8GB GDDR7used, asking price529 €In stock2 h agoBuy
AmazonMSI GeForce RTX 5060 Ti 8G Ventus 2X OC Plus Gaming Graphics CardNew533 €In stock3 h agoBuy
AmazonASUS Dual GeForce RTX 5060 Ti 8GB GDDR7 Graphics Card OC Edition GamingNew548 €In stock3 h agoBuy
eBayPnyNew550 €In stock2 h agoBuy
AmazonGigabyte GeForce RTX 5060 Ti WINDFORCE OC 8G Graphics CardNew554 €In stock3 h agoBuy
AmazonGigabyte GeForce RTX 5060 Ti WINDFORCE MAX OC 8G Graphics CardNew567 €In stock3 h agoBuy
AmazonASUS Dual GeForce RTX 5060 Ti 8GB GDDR7 Gaming Graphics CardNew570 €In stock3 h agoBuy
AmazonGIGABYTE GeForce RTX 5060 Ti Windforce OC 8GNew578 €In stock3 h agoBuy
eBayASUS DUAL-RTX5060TI-O8G NVIDIA Grafikkarteused, asking price579 €In stock2 h agoBuy
eBayASUS DUAL-RTX5060TI-O8G NVIDIA GrafikkarteNew579 €In stock2 h agoBuy
eBayZOTAC GeForce RTX 5060 Ti Twin Edge 8GB GDDR7 DLSS 4 HDMI 3x DPNew580 €In stock2 h agoBuy
eBayASUS DUAL-RTX5060TI-O8G NVIDIA Grafikkarteused, asking price585 €In stock2 h agoBuy
eBayMSI GeForce RTX 5060 TI 8G VENTUS 2X OC PLUS NVIDIA 8 GB GDDR7New586 €In stock2 h agoBuy
eBay8GB Zotac Gaming GeForce RTX 5060 Ti Twin Edge 5060Ti NVIDIA GDDR7New587 €In stock2 h agoBuy
eBayGIGABYTE GeForce RTX 5060 Ti WINDFORCE OC 8G GrafikkarteNew592 €In stock2 h agoBuy
eBayINNO3D GeForce RTX 5060 Ti TWIN X2 8GBNew596 €In stock2 h agoBuy
eBayPalit RTX 5060 Ti Dual OC 8GBNew596 €In stock2 h agoBuy
eBay8GB Gainward GeForce RTX 5060 Ti Ghost GDDR7 NVIDIA RTX5060TiNew597 €In stock2 h agoBuy
AmazonPNY Placa Gráfica GeForce RTX 5060 Ti ARGB OC 8GB GDDR7New599 €In stock3 h agoBuy
AmazonMSI Gaming RTX 5060 Ti 8G Ventus 2X OC Plus Graphics CardNew607 €In stock3 h agoBuy
eBayASUS Prime GeForce RTX 5060 Ti 8GB GDDR7New599 €+ 8 € deliveryIn stock2 h agoBuy
eBayINNO3D GeForce RTX 5060 Ti TWIN X2 OC 8GBNew608 €In stock2 h agoBuy
eBayASUS GeForce RTX 5060 Ti Dual OC 8GB GDDR7 DLSS4New611 €In stock2 h agoBuy
eBayGigabyte GeForce RTX 5060 Ti Windforce OC 8GB GDDR7 DLSS4New611 €In stock2 h agoBuy
AmazonGigabyte GeForce RTX 5060 Ti Gaming OC 8G Graphics CardNew619 €In stock3 h agoBuy
AmazonPNY GeForce RTX 5060 Ti 8GB ARGB OC Triple Fan Graphics Card DLSS 4New634 €In stock3 h agoBuy
AmazonMSI Gaming RTX 5060 Ti 8G Gaming Trio OC Graphics CardNew636 €In stock3 h agoBuy
AmazonASUS TUF Gaming GeForce RTX 5060 Ti OC Edition 8GB GDDR7 Gaming GraphicsNew664 €In stock3 h agoBuy

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 @32kPrefillGood for
Qwen 3.5 9B

Alibaba Qwen

Q4_K_Mfits7.2 GB36k60k with q8 cache

41tok/sest.

497 tok/schat, coding
Qwen 3.5 4B

Alibaba Qwen

Q8_0fits6.1 GB66k110k with q8 cache

50tok/sest.

930 tok/schat, coding
Gemma 4 E4B

Google

Q5_K_Mfits6.9 GB46k77k with q8 cache

43tok/sest.

625 tok/schat, coding
LFM2.5 8B-A1B

Liquid AI

MXFP4fits7.4 GB32k55k with q8 cache

74tok/sest.

2043 tok/schat, coding
Qwen2.5 0.5B

Alibaba Qwen

Q8_0fits1.8 GB32k

298tok/sest.

4449 tok/schat, coding, long documents
Qwen3.5 0.8B

Alibaba Qwen

Q8_0fits2.0 GB256k

225tok/sest.

4180 tok/schat, coding, agents, long documents
Qwen3.5 2B

Alibaba Qwen

Q5_K_Mfits2.6 GB256k

150tok/sest.

1993 tok/schat, coding, agents, long documents
LFM3 1.7B

Liquid AI

Q8_0fits3.0 GB256k

123tok/sest.

2480 tok/schat, coding, agents, long documents
DeepSeek R1 Distill Qwen 1.5B

DeepSeek

Q8_0fits3.5 GB128k

98tok/sest.

1674 tok/schat, coding, long documents
MiniCPM5 2B

openbmb

Q8_0fits4.7 GB89k128k with q8 cache

68tok/sest.

1000 tok/schat, coding, agents, long documents
Spark X2.5 4B

XHToken

mlx-4bitfits4.9 GB93k156k with q8 cache

65tok/sest.

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

Liquid AI

Q8_0fits5.4 GB62k108k with q8 cache

57tok/sest.

1132 tok/schat, coding, agents
LFM2.5 VL 3B

Liquid AI

Q8_0fits5.4 GB32k

57tok/sest.

1038 tok/schat, coding, agents
FrogNano 4B 2609

Microsoft

Q8_0fits6.2 GB63k104k with q8 cache

48tok/sest.

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

IBM

Q8_0fits6.8 GB39k70k with q8 cache

44tok/sest.

725 tok/schat, coding
Ministral 3 3B Instruct 2512

Mistral AI

Q6_Kfits6.8 GB37k68k with q8 cache

44tok/sest.

727 tok/schat, coding, agents
DeepSeek R1 Distill Qwen 7B

DeepSeek

Q4_K_Mfits7.0 GB38k66k with q8 cache

42tok/sest.

489 tok/schat, coding
granite 4.2 3b

IBM

Q8_0fits7.0 GB36k64k with q8 cache

42tok/sest.

760 tok/schat, coding, agents
Qwen 3.8 27B

Alibaba Qwen

UD-Q4_K_Moffload18.4 GB–

4tok/sest.

107 tok/s–
Qwen 3.6 27B

Alibaba Qwen

Q4_K_Moffload18.7 GB–

4tok/sest.

107 tok/s–
Gemma 4 31B

Google

Q4_K_Moffload21.2 GB–

3tok/sest.

91 tok/s–
Qwen 3.6 35B-A3B

Alibaba Qwen

MXFP4offload21.8 GB–

17tok/sest.

721 tok/schat
Qwen 3.5 27B

Alibaba Qwen

Q4_K_Moffload18.6 GB–

4tok/sest.

107 tok/s–
Gemma 4 26B-A4B

Google

MXFP4offload17.1 GB–

14tok/sest.

700 tok/schat
Qwen 3.5 35B-A3B

Alibaba Qwen

Q4_K_Moffload22.1 GB–

17tok/sest.

718 tok/schat
GLM 4.7 Flash

Z.ai

Q4_K_Moffload19.6 GB–

9tok/sest.

391 tok/s–
Devstral Small 2 24B

Mistral AI

Q4_K_Moffload19.2 GB–

4tok/sest.

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

NVIDIA

MXFP4offload22.7 GB–

17tok/sest.

811 tok/schat
gpt-oss 20B

OpenAI

Q4_K_Moffload12.5 GB–

19tok/sest.

676 tok/schat
Kimi Linear 48B-A3B

Moonshot AI

Q4_K_Moffload29.2 GB–

19tok/sest.

570 tok/schat
Qwen3 Coder 30B-A3B

Alibaba Qwen

Q4_K_Moffload21.2 GB–

9tok/sest.

335 tok/schat
Qwen3 32B

Alibaba Qwen

Q4_K_Moffload27.3 GB–

2tok/sest.

59 tok/s–
Gemma 4 12B

Google

Q4_K_Moffload8.3 GB–

23tok/sest.

369 tok/schat, coding
Gemma 3 27B

Google

Q4_K_Moffload19.2 GB–

4tok/sest.

112 tok/s–
Mistral Small 3.2 24B

Mistral AI

Q4_K_Moffload19.2 GB–

4tok/sest.

111 tok/s–
DeepSeek R1 Distill Qwen 32B

DeepSeek

Q4_K_Moffload27.4 GB–

2tok/sest.

67 tok/s–
Ministral 3 14B

Mistral AI

Q4_K_Moffload13.6 GB–

7tok/sest.

196 tok/s–
Qwen3 14B

Alibaba Qwen

Q4_K_Moffload14.3 GB–

6tok/sest.

172 tok/s–
DeepSeek R1 0528 Qwen3 8B

DeepSeek

Q4_K_Moffload10.1 GB13k25k with q8 cache

13tok/sest.

338 tok/schat
Qwen3 8B

Alibaba Qwen

Q4_K_Moffload10.1 GB13k25k with q8 cache

13tok/sest.

338 tok/schat
Phi-4 14B

Microsoft

Q4_K_Moffload15.4 GB–

5tok/sest.

167 tok/s–
Ministral 3 8B

Mistral AI

Q4_K_Moffload10.0 GB13k24k with q8 cache

13tok/sest.

328 tok/schat
Granite 4.2 8B

IBM

Q4_K_Moffload11.0 GB9k17k with q8 cache

10tok/sest.

296 tok/schat
Llama 3.1 8B

Meta

Q4_K_Moffload9.5 GB16k29k with q8 cache

15tok/sest.

370 tok/schat
Mellum2.1 12B A2.5B Thinking

JetBrains

Q4_K_Moffload9.6 GB–

35tok/sest.

1253 tok/schat, coding, agents, long documents
GLM 4.6V Flash

Z.ai

Q4_K_Moffload7.9 GB21k35k with q8 cache

29tok/sest.

327 tok/schat, coding
Kimi VL A3B Thinking 2506

Moonshot AI

Q4_K_Moffload11.7 GB–

21tok/sest.

846 tok/schat, coding
GLM 4 9B 0414

Z.ai

mlx-4bitoffload8.7 GB2k4k with q8 cache

19tok/sest.

325 tok/schat
Kimi VL A3B

Moonshot AI

mlx-5bitoffload12.9 GB–

18tok/sest.

678 tok/schat
DeepSeek R1 Distill Llama 8B

DeepSeek

Q4_K_Moffload9.5 GB16k29k with q8 cache

15tok/sest.

370 tok/schat
Ministral 3 8B Reasoning 2512

Mistral AI

Q4_K_Moffload10.0 GB13k24k with q8 cache

13tok/sest.

328 tok/schat
LFM2.5 24B A2B

Liquid AI

Q4_K_Moffload17.7 GB–

12tok/sest.

720 tok/schat
GLM 4.1V 9B Thinking

Z.ai

mlx-8bitoffload13.1 GB–

7tok/sest.

245 tok/s–
Ministral 3 14B Reasoning 2512

Mistral AI

Q4_K_Moffload13.6 GB–

7tok/sest.

196 tok/s–
DeepSeek R1 Distill Qwen 14B

DeepSeek

Q4_K_Moffload15.3 GB–

6tok/sest.

157 tok/s–
Muse Glimmer 30B

meta-models

Q4_K_Moffload17.5 GB–

4tok/sest.

105 tok/s–
Devstral Small 2507

Mistral AI

Q4_K_Moffload19.2 GB–

4tok/sest.

113 tok/s–
Magistral Small 2506

Mistral AI

Q4_K_Moffload19.2 GB–

4tok/sest.

113 tok/s–
Magistral Small 2507

Mistral AI

Q4_K_Moffload19.2 GB–

4tok/sest.

113 tok/s–
Magistral Small 2509

Mistral AI

Q4_K_Moffload19.2 GB–

4tok/sest.

111 tok/s–
Qwen3.8 27B OBLITERATED

OBLITERATUS

mlx-4bitoffload22.3 GB–

3tok/sest.

100 tok/s–
granite 4.2 30b

IBM

Q4_K_Moffload25.7 GB–

3tok/sest.

79 tok/s–
DeepSeek V4 Flash

DeepSeek

UD-Q2_K_XLwon't run93.8 GB––––
GLM 5.3 Flash

Z.ai

UD-Q2_K_XLwon't run102.6 GB––––
Qwen 3.8 Flash Next

Alibaba Qwen

UD-Q2_K_XLwon't run75.2 GB––––
MiniMax M2.7

MiniMax

UD-Q2_K_XLwon't run78.8 GB––––
Qwen 3.5 122B-A10B

Alibaba Qwen

UD-Q2_K_XLwon't run40.7 GB––––
Nemotron 3 Super 120B-A12B

NVIDIA

UD-Q2_K_XLwon't run52.2 GB––––
Qwen3 Coder Next

Alibaba Qwen

Q4_K_Mwon't run46.9 GB––––
gpt-oss 120B

OpenAI

Q4_K_Mwon't run60.5 GB––––
Mistral Small 4 119B

Mistral AI

UD-Q2_K_XLwon't run39.0 GB––––
GLM 4.5 Air

Z.ai

Q2_Kwon't run48.8 GB––––
Qwen3 Next 80B-A3B

Alibaba Qwen

Q4_K_Mwon't run46.9 GB––––
Llama 3.3 70B

Meta

Q4_K_Mwon't run50.5 GB––––
DeepSeek R1

DeepSeek

Q4_K_Mwon't run379.7 GB––––
DeepSeek R1 0528

DeepSeek

Q4_K_Mwon't run380.2 GB––––
DeepSeek R1 Distill Llama 70B

DeepSeek

Q4_K_Mwon't run50.5 GB––––
DeepSeek R1 Zero

DeepSeek

Q4_K_Mwon't run379.7 GB––––
DeepSeek V3

DeepSeek

Q4_K_Mwon't run379.7 GB––––
DeepSeek V3 0324

DeepSeek

Q4_K_Mwon't run379.7 GB––––
DeepSeek V3.1

DeepSeek

Q4_K_Mwon't run380.6 GB––––
DeepSeek V3.1 Terminus

DeepSeek

Q4_K_Mwon't run380.6 GB––––
DeepSeek V3.2

DeepSeek

Q4_K_Mwon't run380.6 GB––––
DeepSeek V4 Flash 0731

DeepSeek

MXFP4won't run149.2 GB––––
DeepSeek V4 Flash Vision Exp

DeepSeek

MXFP4won't run158.0 GB––––
Devstral 2 123B Instruct 2512

Mistral AI

Q4_K_Mwon't run81.6 GB––––
GLM 4.5

Z.ai

Q4_K_Mwon't run214.0 GB––––
GLM 4.5V

Z.ai

Q4_K_Mwon't run65.9 GB––––
GLM 4.6

Z.ai

Q4_K_Mwon't run213.2 GB––––
GLM 4.6V

Z.ai

Q4_K_Mwon't run72.2 GB––––
GLM 4.7

Z.ai

Q4_K_Mwon't run214.0 GB––––
GLM 5

Z.ai

MXFP4won't run386.0 GB––––
GLM 5.1

Z.ai

MXFP4won't run423.6 GB––––
GLM 5.2

Z.ai

UD-Q4_K_Mwon't run437.5 GB––––
GLM 5.3

Z.ai

Q8_0won't run750.0 GB––––
Kimi Dev 72B

Moonshot AI

Q6_Kwon't run70.8 GB––––
Kimi K2

Moonshot AI

Q4_K_Mwon't run581.2 GB––––
Kimi K2 Instruct 0905

Moonshot AI

Q4_K_Mwon't run581.6 GB––––
Kimi K2 Thinking

Moonshot AI

Q4_K_Mwon't run581.6 GB––––
Kimi K2.5

Moonshot AI

Q4_K_Mwon't run581.6 GB––––
MiniMax M2

MiniMax

Q4_K_Mwon't run137.5 GB––––
MiniMax M2.1

MiniMax

Q4_K_Mwon't run137.5 GB––––
MiniMax M2.5

MiniMax

MXFP4won't run123.9 GB––––
MiniMax M3

MiniMax

MXFP4won't run244.3 GB––––
Mistral Medium 3.5 128B

Mistral AI

Q4_K_Mwon't run81.6 GB––––

Specifications

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

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

Compare with

Questions

How much memory does the NVIDIA GeForce RTX 5060 Ti 8GB have for AI models?
The NVIDIA GeForce RTX 5060 Ti 8GB 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 Ti 8GB can run locally?
Qwen 3.5 9B (Q4_K_M) fits fully in its memory at 32k context and generates at about 41 tok/s, an estimate from its memory bandwidth. 18 of the 129 models we track fit at that context.
Can the NVIDIA GeForce RTX 5060 Ti 8GB run DeepSeek V4 Flash?
No: even at UD-Q2_K_XL, DeepSeek V4 Flash needs about 94 GB at 32k context, more than the NVIDIA GeForce RTX 5060 Ti 8GB and system RAM can hold.
How much does the NVIDIA GeForce RTX 5060 Ti 8GB cost in Germany?
The best new price for the NVIDIA GeForce RTX 5060 Ti 8GB in Germany is 518 € at eBay; used, it starts at 529 € (asking price).

Speeds on this page are for 32k context. See the best hardware for local AI at every budget.

More hardware for local AI