readygpu

NVIDIA GeForce RTX 5070

12 GB · 672 GB/s · 250 W

In short

The NVIDIA GeForce RTX 5070 has 12 GB of GDDR7 memory with 672 GB/s of bandwidth, which sets how fast it generates text. At 32k context it runs 23 of the 113 open models we track fully in memory; the most capable is Gemma 4 12B at Q6_K, at about 39 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5070 in Germany is 699 € at eBay; used, it starts at 780 € (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
eBayGIGABYTE GeForce RTX 5070 Eagle OC ICE SFF 12GB GDDR7 RAM 1x HDMI 3x DP Neu OVPNew699 €+ 5 € deliveryIn stock2 h agoBuy
eBayASUS Dual GeForce RTX 5070 OC 12GB DUAL-RTX5070-O12G Grafikkarte GDDR7 DP/HDMIused, asking price780 €+ 8 € deliveryIn stock2 h agoBuy
eBayGIGABYTE EAGLE OC SFF GeForce RTX 5070 12GB Grafikkarte Raytracingused, asking price800 €In stock2 h agoBuy
eBayGIGABYTE GeForce RTX 5070 GAMING OC 12GB GDDR7 PCIe 5.0 x16 GrafikkarteNew798 €+ 8 € deliveryIn stock2 h agoBuy
eBayASUS PRIME GeForce RTX 5070 OC 12GBNew800 €+ 8 € deliveryIn stock2 h agoBuy
AmazonASUS Dual GeForce RTX 5070 12GB GDDR7 OC Edition Gaming Graphics CardNew817 €In stock3 min agoBuy
AmazonMSI GeForce RTX 5070 12G Ventus 2X OC Gaming Graphics CardNew835 €In stock3 min agoBuy
eBayMSI GeForce RTX 5070 12GB VENTUS 3X OC 12GB GDDR7.used, asking price837 €+ 8 € deliveryIn stock2 h agoBuy
eBayZotac Gaming GeForce RTX 5070 Twin Edgeused, asking price849 €In stock2 h agoBuy
eBayMSI GeForce RTX 12GB 5070 GAMING TRIO OC WHITE Grafikkarte + ARGB MSI Halterused, asking price865 €+ 8 € deliveryIn stock2 h agoBuy
AmazonASUS Prime GeForce RTX 5070 12GB GDDR7 OC Edition Gaming Graphics CardNew879 €In stock8 min agoBuy
AmazonPNY GeForce RTX 5070 12GB Triple Fan Graphics Card DLSS 4New880 €In stock13 h agoBuy
AmazonGIGABYTE GeForce RTX 5070 WINDFORCE SFF 12G Graphics CardNew891 €In stock12 h agoBuy
AmazonMSI GeForce RTX 5070 12G Shadow 2X OC Gaming Graphics CardNew900 €In stock3 min agoBuy
AmazonMSI GeForce RTX 5070 12G Gaming Trio OC Gaming Graphics CardNew904 €In stock3 min agoBuy
AmazonPNY GeForce RTX 5070 12GB ARGB OC Triple Fan Graphics Card DLSS 4New913 €In stock3 min agoBuy
AmazonPNY NVIDIA GeForce RTX 5070 Slim Dual Fan 12GB GDDR7 OC Graphics CardNew916 €In stock13 h agoBuy
eBayASUS GeForce RTX 5070 Dual OC 12GB GDDR7 DLSS4New937 €In stock2 h agoBuy
eBayGrafikkarte ASUS Prime GeForce RTX 5070 OCNew940 €In stock2 h agoBuy
eBayGIGABYTE GeForce RTX 5070 Eagle OC ICE SFF 12GB GDDR7 RAM 1x HDMI 3x DP Neu OVPNew930 €+ 12 € deliveryIn stock2 h agoBuy
eBayInno3D Nvidia GeForce RTX 5070 TwinX2 OC WHITE 12GB GDDR7 RAM HDMI 3x DP Neu OVPNew930 €+ 12 € deliveryIn stock2 h agoBuy
AmazonASUS Prime GeForce RTX 5070 12GB GDDR7 Gaming Graphics CardNew949 €In stock13 h agoBuy
eBayMSI GeForce Nvidia RTX 5070 VENTUS 2X OC 12GB GDDR7 HDMI 3x DPNew940 €+ 12 € deliveryIn stock2 h agoBuy
eBayASUS Dual GeForce RTX 5070 12GB GDDR7 OC Edition Gaming GrafikkarteNew955 €In stock2 h agoBuy
eBayPNY Nvidia GeForce RTX 5070 EPIC-X ARGB OC 12GB GDDR7 RAM 1x HDMI 3x DP Neu 19%New945 €+ 12 € deliveryIn stock2 h agoBuy
eBayGIGABYTE GeForce RTX 5070 GAMING OC 12G GrafikkarteNew960 €In stock2 h agoBuy
eBayGigabyte GeForce RTX 5070 Gaming OC 12 GB GDDR7 PCIe 5.0 x16New968 €In stock2 h agoBuy
eBayASUS PRIME GeForce RTX 5070 12GB GDDR7 OC EditionNew975 €In stock2 h agoBuy
AmazonGigabyte GeForce RTX 5070 WINDFORCE SFF 12G Graphics CardNew975 €In stock13 h agoBuy
eBayZotac GeForce RTX 5070 Twin Edge OC 12 GB GDDR7 PCIe 5.0 x16New980 €In stock2 h agoBuy
AmazonASUS Prime GeForce RTX 5070 12GB GDDR7 White OC Edition Graphics CardNew993 €In stock13 h agoBuy
AmazonNVIDIANew1.000 €In stock12 h agoBuy
eBayASUS PRIME GeForce RTX 5070 12 GB GDDR7 OC Edition Gaming GrafikkarteNew1.003 €In stock2 h agoBuy
eBayMSI GeForce RTX 5070 Gaming Trio OC 12 GB GDDR7 PCIe 5.0 x16New1.013 €In stock2 h agoBuy
AmazonASUS The T1 GeForce RTX 5070 12GB GDDR7 Graphics CardNew999 €+ 21 € deliveryIn stock13 h agoBuy
AmazonGigabyte Aorus GeForce RTX 5070 Master 12G Graphics CardNew1.046 €In stock13 h agoBuy

Used on eBay: median asking price 810 €, most between 790 € and 853 € (8 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 @32kPrefillGood for
Gemma 4 12B

Google

Q6_Kfits10.8 GB59k100k with q8 cache

39tok/sest.

1044 tok/schat, coding, long documents
Qwen 3.5 9B

Alibaba Qwen

Q8_0fits10.8 GB47k79k with q8 cache

39tok/sest.

1301 tok/schat, coding
DeepSeek R1 0528 Qwen3 8B

DeepSeek

Q5_K_Mfits10.8 GB35k65k with q8 cache

39tok/sest.

1071 tok/schat, coding
Qwen3 8B

Alibaba Qwen

Q5_K_Mfits10.8 GB35k40k with q8 cache

39tok/sest.

1071 tok/schat, coding
Qwen 3.5 4B

Alibaba Qwen

Q8_0fits6.1 GB174k256k with q8 cache

74tok/sest.

2433 tok/schat, coding, long documents
Ministral 3 8B

Mistral AI

Q5_K_Mfits10.8 GB36k66k with q8 cache

39tok/sest.

1035 tok/schat, coding
Granite 4.2 8B

IBM

Q4_K_Mfits11.0 GB34k62k with q8 cache

38tok/sest.

985 tok/schat, coding, agents
Gemma 4 E4B

Google

Q8_0fits9.4 GB91k128k with q8 cache

45tok/sest.

1634 tok/schat, coding, long documents
LFM2.5 8B-A1B

Liquid AI

Q8_0fits10.8 GB43k75k with q8 cache

94tok/sest.

5344 tok/schat, coding
Llama 3.1 8B

Meta

Q6_Kfits11.0 GB34k63k with q8 cache

38tok/sest.

1132 tok/schat, coding
Qwen2.5 0.5B

Alibaba Qwen

Q8_0fits1.8 GB32k

446tok/sest.

11638 tok/schat, coding, long documents
Qwen3.5 0.8B

Alibaba Qwen

Q8_0fits2.0 GB256k

338tok/sest.

10932 tok/schat, coding, agents, long documents
Qwen3.5 2B

Alibaba Qwen

Q5_K_Mfits2.6 GB256k

224tok/sest.

5212 tok/schat, coding, agents, long documents
DeepSeek R1 Distill Qwen 1.5B

DeepSeek

Q8_0fits3.5 GB128k

147tok/sest.

4378 tok/schat, coding, long documents
MiniCPM5 2B

openbmb

Q8_0fits4.7 GB128k

102tok/sest.

2615 tok/schat, coding, agents, long documents
LFM2.5 2.6B

Liquid AI

Q8_0fits5.4 GB124k128k with q8 cache

85tok/sest.

2962 tok/schat, coding, agents, long documents
LFM2.5 VL 3B

Liquid AI

Q8_0fits5.4 GB32k

85tok/sest.

2716 tok/schat, coding, agents, long documents
granite vision 4.1 4b

IBM

Q8_0fits6.8 GB87k128k with q8 cache

66tok/sest.

1897 tok/schat, coding
granite 4.2 3b

IBM

Q8_0fits7.0 GB84k128k with q8 cache

63tok/sest.

1989 tok/schat, coding, agents
GLM 4.6V Flash

Z.ai

Q4_K_Mfits7.9 GB110k128k with q8 cache

56tok/sest.

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

DeepSeek

Q8_0fits10.2 GB52k90k with q8 cache

42tok/sest.

1279 tok/schat, coding
Ministral 3 8B Reasoning 2512

Mistral AI

Q5_K_Mfits10.8 GB36k66k with q8 cache

39tok/sest.

1035 tok/schat, coding, agents
DeepSeek R1 Distill Llama 8B

DeepSeek

Q6_Kfits11.0 GB34k63k with q8 cache

38tok/sest.

1132 tok/schat, coding
Qwen 3.8 27B

Alibaba Qwen

UD-Q4_K_Moffload18.4 GB–

6tok/sest.

342 tok/s–
Qwen 3.6 27B

Alibaba Qwen

Q4_K_Moffload18.7 GB–

6tok/sest.

339 tok/s–
Gemma 4 31B

Google

Q4_K_Moffload21.2 GB–

5tok/sest.

285 tok/s–
Qwen 3.6 35B-A3B

Alibaba Qwen

MXFP4offload21.8 GB–

23tok/sest.

2255 tok/schat, coding
Qwen 3.5 27B

Alibaba Qwen

Q4_K_Moffload18.6 GB–

6tok/sest.

340 tok/s–
Gemma 4 26B-A4B

Google

UD-Q4_K_Moffload17.5 GB–

21tok/sest.

2229 tok/schat, coding
Qwen 3.5 35B-A3B

Alibaba Qwen

Q4_K_Moffload22.1 GB–

22tok/sest.

2242 tok/schat, coding
GLM 4.7 Flash

Z.ai

Q4_K_Moffload19.6 GB–

13tok/sest.

1237 tok/schat
Devstral Small 2 24B

Mistral AI

Q4_K_Moffload19.2 GB–

5tok/sest.

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

NVIDIA

UD-Q6_K_XLoffload33.7 GB–

13tok/sest.

2171 tok/s–
gpt-oss 20B

OpenAI

Q4_K_Moffload12.5 GB–

49tok/sest.

2266 tok/schat, coding, agents, long documents
Kimi Linear 48B-A3B

Moonshot AI

Q4_K_Moffload29.2 GB–

22tok/sest.

1725 tok/schat, coding, long documents
Qwen3 Coder 30B-A3B

Alibaba Qwen

Q4_K_Moffload21.2 GB–

12tok/sest.

1050 tok/schat
Qwen3 32B

Alibaba Qwen

Q4_K_Moffload27.3 GB–

3tok/sest.

179 tok/s–
Gemma 3 27B

Google

Q4_K_Moffload19.2 GB–

6tok/sest.

356 tok/s–
Mistral Small 3.2 24B

Mistral AI

Q4_K_Moffload19.2 GB–

5tok/sest.

353 tok/s–
DeepSeek R1 Distill Qwen 32B

DeepSeek

Q4_K_Moffload27.4 GB–

3tok/sest.

205 tok/s–
Ministral 3 14B

Mistral AI

Q4_K_Moffload13.6 GB18k34k with q8 cache

14tok/sest.

648 tok/schat
Qwen3 14B

Alibaba Qwen

Q4_K_Moffload14.3 GB14k26k with q8 cache

12tok/sest.

566 tok/schat
Phi-4 14B

Microsoft

Q4_K_Moffload15.4 GB12k16k with q8 cache

9tok/sest.

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

JetBrains

Q6_Koffload12.0 GB–

63tok/sest.

3727 tok/schat, coding, agents, long documents
Kimi VL A3B

Moonshot AI

mlx-5bitoffload12.9 GB–

43tok/sest.

2687 tok/schat, coding, agents
LFM2.5 24B A2B

Liquid AI

Q4_K_Moffload17.7 GB–

18tok/sest.

2309 tok/schat
GLM 4.1V 9B Thinking

Z.ai

mlx-8bitoffload13.1 GB–

16tok/sest.

816 tok/schat
DeepSeek R1 Distill Qwen 14B

DeepSeek

Q4_K_Moffload15.3 GB12k22k with q8 cache

10tok/sest.

513 tok/schat
Devstral Small 2507

Mistral AI

Q4_K_Moffload19.2 GB–

5tok/sest.

359 tok/s–
Magistral Small 2506

Mistral AI

Q4_K_Moffload19.2 GB–

5tok/sest.

359 tok/s–
Magistral Small 2507

Mistral AI

Q4_K_Moffload19.2 GB–

5tok/sest.

359 tok/s–
Magistral Small 2509

Mistral AI

Q4_K_Moffload19.2 GB–

5tok/sest.

353 tok/s–
granite 4.2 30b

IBM

Q4_K_Moffload25.7 GB–

3tok/sest.

241 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 V3 0324

DeepSeek

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

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

Q8_0won't run135.6 GB––––
GLM 4.5V

Z.ai

Q4_K_Mwon't run65.9 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 5.1

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 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

UD-Q4_K_Mwon't run251.4 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 5070
Memory
12 GB GDDR7
Memory bus
192-bit
Memory bandwidth
672 GB/s
FP16 compute
62 TFLOPS
Software
CUDA
Board power
250 W
PCIe generation
Gen 5
PCIe lanes
x16

Compare with

Questions

How much memory does the NVIDIA GeForce RTX 5070 have for AI models?
The NVIDIA GeForce RTX 5070 has 12 GB of GDDR7 memory with 672 GB/s of bandwidth, which sets how fast it generates text.
What is the best model the NVIDIA GeForce RTX 5070 can run locally?
Gemma 4 12B (Q6_K) fits fully in its memory at 32k context and generates at about 39 tok/s, an estimate from its memory bandwidth. 23 of the 113 models we track fit at that context.
Can the NVIDIA GeForce RTX 5070 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 5070 and system RAM can hold.
How much does the NVIDIA GeForce RTX 5070 cost in Germany?
The best new price for the NVIDIA GeForce RTX 5070 in Germany is 699 € at eBay; used, it starts at 780 € (asking price).

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