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 128k context it runs 11 of the 113 open models we track fully in memory; the most capable is Gemma 4 12B at Q4_K_M, at about 43 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 stock41 min agoBuy
AmazonMSI GeForce RTX 5070 12G Ventus 2X OC Gaming Graphics CardNew835 €In stock41 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 stock46 min agoBuy
AmazonPNY GeForce RTX 5070 12GB Triple Fan Graphics Card DLSS 4New880 €In stock35 min agoBuy
AmazonGigabyte GeForce RTX 5070 Eagle OC Ice SFF 12G Graphics CardNew885 €In stock35 min agoBuy
AmazonGIGABYTE GeForce RTX 5070 WINDFORCE SFF 12G Graphics CardNew891 €In stock24 min agoBuy
AmazonMSI GeForce RTX 5070 12G Shadow 2X OC Gaming Graphics CardNew900 €In stock41 min agoBuy
AmazonMSI GeForce RTX 5070 12G Gaming Trio OC Gaming Graphics CardNew904 €In stock41 min agoBuy
AmazonPNY GeForce RTX 5070 12GB ARGB OC Triple Fan Graphics Card DLSS 4New913 €In stock41 min agoBuy
AmazonPNY NVIDIA GeForce RTX 5070 Slim Dual Fan 12GB GDDR7 OC Graphics CardNew916 €In stock35 min 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 stock35 min 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 stock35 min 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 stock35 min agoBuy
AmazonNVIDIANew1.000 €In stock24 min 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 stock35 min agoBuy
AmazonGigabyte Aorus GeForce RTX 5070 Master 12G Graphics CardNew1.046 €In stock35 min agoBuy
AmazonASUS ROG Strix GeForce RTX 5070 OC Edition 12GB GDDR7 Gaming Graphics CardNew1.344 €+ 41 € deliveryIn stock24 min 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 @128kPrefillGood for
Gemma 4 12B

Google

Q4_K_Mfits10.4 GB174k256k with q8 cache

43tok/sest.

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

Alibaba Qwen

Q4_K_Mfits10.8 GB144k238k with q8 cache

42tok/sest.

1000 tok/schat, coding, long documents
Qwen 3.5 4B

Alibaba Qwen

Q8_0fits9.7 GB174k256k with q8 cache

47tok/sest.

1558 tok/schat, coding, long documents
Gemma 4 E4B

Google

Q5_K_Mfits10.1 GB128k

45tok/sest.

1402 tok/schat, coding, long documents
Qwen2.5 0.5B

Alibaba Qwen

Q8_0fits3.4 GB32k

195tok/sest.

4211 tok/schat, coding, long documents
Qwen3.5 0.8B

Alibaba Qwen

Q8_0fits3.7 GB256k

171tok/sest.

5616 tok/schat, coding, agents, long documents
Qwen3.5 2B

Alibaba Qwen

Q5_K_Mfits4.3 GB256k

136tok/sest.

3591 tok/schat, coding, agents, long documents
DeepSeek R1 Distill Qwen 1.5B

DeepSeek

Q8_0fits6.7 GB128k

74tok/sest.

1882 tok/schat, coding, long documents
MiniCPM5 2B

openbmb

Q8_0fits9.2 GB128k

50tok/sest.

1012 tok/schat, coding, agents, long documents
LFM2.5 2.6B

Liquid AI

Q6_Kfits11.0 GB128k

41tok/sest.

1298 tok/schat, coding, agents, long documents
LFM2.5 VL 3B

Liquid AI

Q6_Kfits11.0 GB32k

41tok/sest.

1248 tok/schat, coding, agents, long documents
Qwen 3.8 27B

Alibaba Qwen

UD-Q4_K_Moffload24.9 GB–

3tok/sest.

225 tok/s–
Qwen 3.6 27B

Alibaba Qwen

Q4_K_Moffload25.3 GB–

3tok/sest.

223 tok/s–
Gemma 4 31B

Google

Q4_K_Moffload29.3 GB–

3tok/sest.

200 tok/s–
Qwen 3.6 35B-A3B

Alibaba Qwen

MXFP4offload24.2 GB–

11tok/sest.

1104 tok/schat, coding
Qwen 3.5 27B

Alibaba Qwen

Q4_K_Moffload25.2 GB–

3tok/sest.

224 tok/s–
Gemma 4 26B-A4B

Google

UD-Q4_K_Moffload19.9 GB–

11tok/sest.

1463 tok/schat, coding
Qwen 3.5 35B-A3B

Alibaba Qwen

Q4_K_Moffload24.5 GB–

11tok/sest.

1098 tok/schat, coding
GLM 4.7 Flash

Z.ai

Q4_K_Moffload25.1 GB–

5tok/sest.

513 tok/schat
Devstral Small 2 24B

Mistral AI

Q4_K_Moffload34.8 GB–

2tok/sest.

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

NVIDIA

UD-Q6_K_XLoffload34.8 GB–

10tok/sest.

1298 tok/s–
Kimi Linear 48B-A3B

Moonshot AI

Q4_K_Moffload30.5 GB–

16tok/sest.

758 tok/schat, coding, long documents
gpt-oss 20B

OpenAI

Q4_K_Moffload15.3 GB–

16tok/sest.

1090 tok/schat, coding, agents, long documents
Qwen3 Coder 30B-A3B

Alibaba Qwen

Q4_K_Moffload30.7 GB–

3tok/sest.

293 tok/schat
Gemma 3 27B

Google

Q4_K_Moffload27.3 GB–

3tok/sest.

265 tok/s–
Mistral Small 3.2 24B

Mistral AI

Q4_K_Moffload34.8 GB–

2tok/sest.

178 tok/s–
Ministral 3 14B

Mistral AI

Q4_K_Moffload29.1 GB18k34k with q8 cache

3tok/sest.

243 tok/schat
Qwen3 14B

Alibaba Qwen

Q4_K_Moffload29.8 GB14k26k with q8 cache

3tok/sest.

205 tok/schat
DeepSeek R1 0528 Qwen3 8B

DeepSeek

Q4_K_Moffload24.1 GB41k74k with q8 cache

4tok/sest.

336 tok/schat, coding
Qwen3 8B

Alibaba Qwen

Q4_K_Moffload24.1 GB40k

4tok/sest.

336 tok/schat, coding
Phi-4 14B

Microsoft

Q4_K_Moffload34.7 GB12k16k with q8 cache

2tok/sest.

195 tok/schat
Ministral 3 8B

Mistral AI

Q4_K_Moffload23.3 GB42k76k with q8 cache

4tok/sest.

346 tok/schat, coding
Granite 4.2 8B

IBM

Q4_K_Moffload26.6 GB34k62k with q8 cache

3tok/sest.

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

Liquid AI

UD-Q4_K_Moffload12.4 GB108k125k with q8 cache

22tok/sest.

1771 tok/schat, coding, long documents
Llama 3.1 8B

Meta

Q4_K_Moffload22.0 GB46k84k with q8 cache

4tok/sest.

382 tok/schat, coding
Mellum2.1 12B A2.5B Thinking

JetBrains

Q6_Koffload13.9 GB–

25tok/sest.

1906 tok/schat, coding, agents, long documents
GLM 4.6V Flash

Z.ai

Q4_K_Moffload12.2 GB110k128k with q8 cache

24tok/sest.

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

DeepSeek

Q4_K_Moffload12.8 GB104k128k with q8 cache

19tok/sest.

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

IBM

Q4_K_Moffload13.4 GB104k128k with q8 cache

15tok/sest.

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

IBM

Q4_K_Moffload13.6 GB101k128k with q8 cache

14tok/sest.

728 tok/schat, coding, agents
Kimi VL A3B

Moonshot AI

mlx-5bitoffload16.3 GB–

13tok/sest.

1093 tok/schat, coding, agents
GLM 4.1V 9B Thinking

Z.ai

mlx-8bitoffload17.4 GB–

7tok/sest.

340 tok/schat
DeepSeek R1 Distill Llama 8B

DeepSeek

Q4_K_Moffload22.0 GB46k84k with q8 cache

4tok/sest.

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

Liquid AI

Q4_K_Moffload25.7 GB–

4tok/sest.

707 tok/schat
Ministral 3 8B Reasoning 2512

Mistral AI

Q4_K_Moffload23.3 GB42k76k with q8 cache

4tok/sest.

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

DeepSeek

Q4_K_Moffload33.8 GB12k22k with q8 cache

2tok/sest.

174 tok/schat
Devstral Small 2507

Mistral AI

Q4_K_Moffload34.8 GB–

2tok/sest.

179 tok/s–
Magistral Small 2506

Mistral AI

Q4_K_Moffload34.8 GB–

2tok/sest.

179 tok/s–
Magistral Small 2507

Mistral AI

Q4_K_Moffload34.8 GB–

2tok/sest.

179 tok/s–
Magistral Small 2509

Mistral AI

Q4_K_Moffload34.8 GB–

2tok/sest.

178 tok/s–
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 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 (Q4_K_M) fits fully in its memory at 128k context and generates at about 43 tok/s, an estimate from its memory bandwidth. 11 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 102 GB at 128k 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 128k context. See the best hardware for local AI at every budget.