readygpu

NVIDIA GeForce RTX 4090

24 GB · 1,008 GB/s · 450 W

In short

The NVIDIA GeForce RTX 4090 has 24 GB of GDDR6X memory with 1,008 GB/s of bandwidth, which sets how fast it generates text. At 64k context it runs 40 of the 113 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q4_K_M, at about 29 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 4090 in Germany is 3.955 € at eBay; used, it starts at 2.800 € (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 4090 Gaming X Trio 24Gused, asking price2.800 €In stock1 h agoBuy
eBayMSI GeForce RTX 4090 Ventus 3X 24 GB GDDR6Xused, asking price2.830 €In stock1 h agoBuy
eBayPalit RTX 4090 24GB GDDR6X VRAM GameRock OmniBlackused, asking price2.850 €In stock1 h agoBuy
eBayGIGABYTE GeForce RTX 4090 AERO OC 24G Grafikkarteused, asking price2.849 €+ 15 € deliveryIn stock1 h agoBuy
eBayPalit GeForce RTX 4090 GameRock OC 24GB GDDR6X Grafikkarteused, asking price2.850 €+ 15 € deliveryIn stock1 h agoBuy
eBayMSI GeForce RTX 4090 GAMING X TRIO 24GB GDDR6Xused, asking price2.990 €In stock1 h agoBuy
eBayASUS ROG Strix GeForce RTX 4090 OC White 24GB Grafikkarteused, asking price3.000 €In stock1 h agoBuy
eBayPalit GeForce RTX 4090 GameRock OC 24GB GDDR6X Grafikkarteused, asking price3.000 €In stock1 h agoBuy
eBayGigabyte Geforce RTX 4090 Windforce v2 24G Grafikkarteused, asking price3.000 €In stock1 h agoBuy
eBayMSI GeForce RTX 4090 SUPRIM x Liquid 24g NVIDIA 24GB GDDR6X Grafikkarteused, asking price3.000 €+ 8 € deliveryIn stock5 h agoBuy
eBayMSI GeForce RTX 4090 SUPRIM LIQUID 24GB GDDR6X Grafikkarteused, asking price3.150 €In stock1 h agoBuy
eBayPalit GeForce RTX 4090 GameRock OC 24GB GDDR6X Grafikkarteused, asking price3.150 €+ 8 € deliveryIn stock1 h agoBuy
eBayNVIDIA GeForce RTX 4090 Founders Edition 24GB Grafikkarte inkl. Stromadapterused, asking price3.200 €+ 28 € deliveryIn stock1 h agoBuy
eBayASUS TUF Gaming GeForce RTX 4090 24GB GDDR6X GPU Grafikkarteused, asking price3.299 €In stock1 h agoBuy
eBay24GB ASUS TUF Gaming Nvidia RTX O24G OG OC Edition GDDR6X 4090 GrafikkarteNew3.955 €+ 15 € deliveryIn stock1 h agoBuy

Used on eBay: median asking price 3.200 €, most between 2.955 € and 3.463 € (24 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 @64kPrefillGood for
Qwen 3.8 27B

Alibaba Qwen

Q4_K_Mfits21.5 GB92k161k with q8 cache

29tok/sest.

1085 tok/schat, coding, agents
Qwen 3.6 27B

Alibaba Qwen

Q5_K_Mfits23.4 GB64k112k with q8 cache

26tok/sest.

1085 tok/schat, coding
Qwen 3.6 35B-A3B

Alibaba Qwen

Q4_K_Mfits23.1 GB74k116k with q8 cache

115tok/sest.

6531 tok/schat, coding, agents, long documents
Qwen 3.5 27B

Alibaba Qwen

Q4_K_Mfits20.8 GB101k178k with q8 cache

30tok/sest.

1085 tok/schat, coding, agents
Gemma 4 26B-A4B

Google

UD-Q5_K_Mfits22.2 GB110k178k with q8 cache

78tok/sest.

6687 tok/schat, coding, agents, long documents
Qwen 3.5 35B-A3B

Alibaba Qwen

Q4_K_Mfits22.9 GB84k131k with q8 cache

116tok/sest.

6531 tok/schat, coding, agents, long documents
GLM 4.7 Flash

Z.ai

Q4_K_Mfits21.4 GB98k169k with q8 cache

57tok/sest.

3240 tok/schat, coding, agents, long documents
gpt-oss 20B

OpenAI

MXFP4fits13.9 GB128k

93tok/sest.

4999 tok/schat, coding, agents, long documents
Gemma 4 12B

Google

Q8_0fits14.2 GB256k

44tok/sest.

2571 tok/schat, coding, long documents
Qwen 3.5 9B

Alibaba Qwen

Q8_0fits12.0 GB256k

53tok/sest.

3146 tok/schat, coding, long documents
Gemma 3 27B

Google

Q4_K_Mfits21.9 GB81k128k with q8 cache

28tok/sest.

1215 tok/schat, coding
Ministral 3 14B

Mistral AI

Q6_Kfits21.4 GB76k139k with q8 cache

29tok/sest.

1504 tok/schat, coding
Qwen3 14B

Alibaba Qwen

Q6_Kfits22.4 GB40k

27tok/sest.

1317 tok/schat, coding
DeepSeek R1 0528 Qwen3 8B

DeepSeek

Q8_0fits18.2 GB99k128k with q8 cache

34tok/sest.

2079 tok/schat, coding
Qwen3 8B

Alibaba Qwen

Q8_0fits18.2 GB40k

34tok/sest.

2079 tok/schat, coding
Phi-4 14B

Microsoft

Q5_K_Mfits23.3 GB16k

26tok/sest.

1322 tok/schat, coding
Qwen 3.5 4B

Alibaba Qwen

Q8_0fits7.3 GB256k

94tok/sest.

5454 tok/schat, coding, long documents
Ministral 3 8B

Mistral AI

Q8_0fits18.0 GB103k187k with q8 cache

34tok/sest.

2057 tok/schat, coding
Granite 4.2 8B

IBM

Q8_0fits19.8 GB86k128k with q8 cache

31tok/sest.

1901 tok/schat, coding, agents
Gemma 4 E4B

Google

Q8_0fits10.5 GB128k

62tok/sest.

4121 tok/schat, coding, long documents
LFM2.5 8B-A1B

Liquid AI

Q8_0fits12.5 GB125k

88tok/sest.

8795 tok/schat, coding, long documents
Llama 3.1 8B

Meta

Q6_Kfits15.2 GB126k128k with q8 cache

41tok/sest.

2234 tok/schat, coding, long documents
Qwen2.5 0.5B

Alibaba Qwen

Q8_0fits2.3 GB32k

468tok/sest.

19505 tok/schat, coding, long documents
Qwen3.5 0.8B

Alibaba Qwen

Q8_0fits2.6 GB256k

382tok/sest.

22115 tok/schat, coding, agents, long documents
Qwen3.5 2B

Alibaba Qwen

Q5_K_Mfits3.2 GB256k

277tok/sest.

12056 tok/schat, coding, agents, long documents
DeepSeek R1 Distill Qwen 1.5B

DeepSeek

Q8_0fits4.6 GB128k

166tok/sest.

8078 tok/schat, coding, long documents
MiniCPM5 2B

openbmb

Q8_0fits6.2 GB128k

114tok/sest.

4553 tok/schat, coding, agents, long documents
Mellum2.1 12B A2.5B Thinking

JetBrains

Q8_0fits14.0 GB128k

103tok/sest.

8150 tok/schat, coding, agents, long documents
LFM2.5 2.6B

Liquid AI

Q8_0fits7.5 GB128k

91tok/sest.

5522 tok/schat, coding, agents, long documents
LFM2.5 VL 3B

Liquid AI

Q8_0fits7.5 GB32k

91tok/sest.

5192 tok/schat, coding, agents, long documents
Kimi VL A3B

Moonshot AI

mlx-8bitfits19.6 GB128k

71tok/sest.

5605 tok/schat, coding, agents, long documents
granite vision 4.1 4b

IBM

Q8_0fits9.4 GB128k

70tok/sest.

3467 tok/schat, coding, long documents
granite 4.2 3b

IBM

Q8_0fits9.7 GB128k

68tok/sest.

3580 tok/schat, coding, agents, long documents
LFM2.5 24B A2B

Liquid AI

Q5_K_Mfits23.3 GB65k115k with q8 cache

54tok/sest.

5038 tok/schat, coding, agents
DeepSeek R1 Distill Qwen 7B

DeepSeek

Q8_0fits12.1 GB128k

53tok/sest.

2616 tok/schat, coding, long documents
GLM 4.6V Flash

Z.ai

Q8_0fits12.9 GB128k

49tok/sest.

1765 tok/schat, coding, agents, long documents
GLM 4.1V 9B Thinking

Z.ai

mlx-8bitfits14.5 GB64k

43tok/sest.

1765 tok/schat, coding, long documents
DeepSeek R1 Distill Llama 8B

DeepSeek

Q8_0fits17.0 GB112k128k with q8 cache

37tok/sest.

2234 tok/schat, coding
Ministral 3 8B Reasoning 2512

Mistral AI

Q8_0fits18.0 GB103k187k with q8 cache

34tok/sest.

2057 tok/schat, coding, agents
DeepSeek R1 Distill Qwen 14B

DeepSeek

Q5_K_Mfits22.9 GB66k122k with q8 cache

27tok/sest.

1202 tok/schat, coding
Qwen 3.5 122B-A10B

Alibaba Qwen

UD-Q2_K_XLoffload41.7 GB–

13tok/sest.

1648 tok/schat
Gemma 4 31B

Google

Q4_K_Moffload23.9 GB57k110k with q8 cache

21tok/sest.

977 tok/schat, coding
Qwen3 Coder Next

Alibaba Qwen

Q4_K_Moffload47.8 GB–

14tok/sest.

3591 tok/schat
Mistral Small 4 119B

Mistral AI

UD-Q2_K_XLoffload39.9 GB–

18tok/sest.

1653 tok/schat, coding
Devstral Small 2 24B

Mistral AI

Q4_K_Moffload24.4 GB57k105k with q8 cache

17tok/sest.

1040 tok/schat, coding, agents
Qwen3 Next 80B-A3B

Alibaba Qwen

Q4_K_Moffload47.8 GB–

17tok/sest.

4097 tok/schat, coding
Nemotron 3.5 Lightning 30B-A3B

NVIDIA

UD-Q6_K_XLoffload34.1 GB–

22tok/sest.

6487 tok/schat, coding, long documents
Kimi Linear 48B-A3B

Moonshot AI

Q4_K_Moffload29.6 GB–

47tok/sest.

4562 tok/schat, coding, long documents
Qwen3 Coder 30B-A3B

Alibaba Qwen

Q4_K_Moffload24.4 GB54k97k with q8 cache

32tok/sest.

2280 tok/schat, coding, agents
Qwen3 32B

Alibaba Qwen

Q4_K_Moffload35.5 GB16k30k with q8 cache

4tok/sest.

437 tok/schat
Mistral Small 3.2 24B

Mistral AI

Q4_K_Moffload24.4 GB57k105k with q8 cache

17tok/sest.

1040 tok/schat, coding
DeepSeek R1 Distill Qwen 32B

DeepSeek

Q4_K_Moffload35.6 GB16k30k with q8 cache

4tok/sest.

540 tok/schat
Devstral Small 2507

Mistral AI

Q4_K_Moffload24.4 GB57k105k with q8 cache

17tok/sest.

1054 tok/schat, coding, agents
Magistral Small 2506

Mistral AI

Q4_K_Moffload24.4 GB40k

17tok/sest.

1054 tok/schat, coding
Magistral Small 2507

Mistral AI

Q4_K_Moffload24.4 GB40k

17tok/sest.

1054 tok/schat, coding, agents
Magistral Small 2509

Mistral AI

Q4_K_Moffload24.4 GB57k105k with q8 cache

17tok/sest.

1040 tok/schat, coding, agents
granite 4.2 30b

IBM

Q4_K_Moffload33.9 GB23k42k with q8 cache

4tok/sest.

646 tok/schat
DeepSeek V4 Flash

DeepSeek

UD-Q2_K_XLwon't run96.6 GB––––
GLM 5.3 Flash

Z.ai

UD-Q2_K_XLwon't run103.1 GB––––
Qwen 3.8 Flash Next

Alibaba Qwen

UD-Q2_K_XLwon't run76.1 GB––––
MiniMax M2.7

MiniMax

UD-Q2_K_XLwon't run86.7 GB––––
Nemotron 3 Super 120B-A12B

NVIDIA

UD-Q2_K_XLwon't run52.6 GB––––
gpt-oss 120B

OpenAI

Q4_K_Mwon't run61.8 GB––––
GLM 4.5 Air

Z.ai

Q2_Kwon't run54.8 GB––––
Llama 3.3 70B

Meta

Q4_K_Mwon't run60.7 GB––––
DeepSeek R1

DeepSeek

Q4_K_Mwon't run382.0 GB––––
DeepSeek R1 0528

DeepSeek

Q4_K_Mwon't run382.5 GB––––
DeepSeek R1 Distill Llama 70B

DeepSeek

Q4_K_Mwon't run60.7 GB––––
DeepSeek V3 0324

DeepSeek

Q4_K_Mwon't run382.0 GB––––
DeepSeek V3.1

DeepSeek

Q4_K_Mwon't run382.9 GB––––
DeepSeek V3.2

DeepSeek

Q4_K_Mwon't run382.9 GB––––
DeepSeek V4 Flash 0731

DeepSeek

MXFP4won't run152.1 GB––––
DeepSeek V4 Flash Vision Exp

DeepSeek

MXFP4won't run160.9 GB––––
Devstral 2 123B Instruct 2512

Mistral AI

Q8_0won't run146.8 GB––––
GLM 4.5V

Z.ai

Q4_K_Mwon't run71.8 GB––––
GLM 4.6V

Z.ai

Q4_K_Mwon't run78.2 GB––––
GLM 4.7

Z.ai

Q4_K_Mwon't run225.7 GB––––
GLM 5.1

Z.ai

MXFP4won't run426.5 GB––––
GLM 5.2

Z.ai

UD-Q4_K_Mwon't run440.4 GB––––
GLM 5.3

Z.ai

Q8_0won't run752.9 GB––––
Kimi K2

Moonshot AI

Q4_K_Mwon't run583.5 GB––––
Kimi K2 Instruct 0905

Moonshot AI

Q4_K_Mwon't run583.9 GB––––
Kimi K2 Thinking

Moonshot AI

Q4_K_Mwon't run583.9 GB––––
Kimi K2.5

Moonshot AI

Q4_K_Mwon't run583.9 GB––––
MiniMax M2

MiniMax

Q4_K_Mwon't run145.4 GB––––
MiniMax M2.1

MiniMax

Q4_K_Mwon't run145.4 GB––––
MiniMax M2.5

MiniMax

MXFP4won't run131.8 GB––––
MiniMax M3

MiniMax

UD-Q4_K_Mwon't run255.3 GB––––
Mistral Medium 3.5 128B

Mistral AI

Q4_K_Mwon't run92.8 GB––––

Specifications

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

GPU
GeForce RTX 4090
Memory
24 GB GDDR6X
Memory bus
384-bit
Memory bandwidth
1,008 GB/s
FP16 compute
165 TFLOPS
Software
CUDA
Board power
450 W
PCIe generation
Gen 4
PCIe lanes
x16

Compare with

Questions

How much memory does the NVIDIA GeForce RTX 4090 have for AI models?
The NVIDIA GeForce RTX 4090 has 24 GB of GDDR6X memory with 1,008 GB/s of bandwidth, which sets how fast it generates text.
What is the best model the NVIDIA GeForce RTX 4090 can run locally?
Qwen 3.8 27B (Q4_K_M) fits fully in its memory at 64k context and generates at about 29 tok/s, an estimate from its memory bandwidth. 40 of the 113 models we track fit at that context.
Can the NVIDIA GeForce RTX 4090 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 4090 and system RAM can hold.
How much does the NVIDIA GeForce RTX 4090 cost in Germany?
The best new price for the NVIDIA GeForce RTX 4090 in Germany is 3.955 € at eBay; used, it starts at 2.800 € (asking price).

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