readygpu

NVIDIA GeForce RTX 5090

32 GB · 1,792 GB/s · 575 W

In short

The NVIDIA GeForce RTX 5090 has 32 GB of GDDR7 memory with 1,792 GB/s of bandwidth, which sets how fast it generates text. At 32k context it runs 62 of the 128 open models we track fully in memory; the most capable is Qwen 3.8 27B at Q8_0, at about 35 tok/s (estimated). The best new price for the NVIDIA GeForce RTX 5090 in the US is $4,921 at eBay; used, it starts at $6,450 (asking price).

Updated . Speeds are estimates; how they are worked out.

Prices

Every retailer we track in the US, cheapest first. Buy links may earn us a commission.

RetailerConditionPriceStockCheckedBuy
eBayGIGABYTE AORUS GeForce RTX 5090 32GB GDDR7 PCI Express 5.0 ATX Graphics Card GV-New$4,921In stock47 min agoBuy
eBayGIGABYTE AORUS GeForce RTX 5090 32GB GDDR7 PCI Express 5.0 ATX Graphics Card GV-New$5,654In stock4 h agoBuy
eBayASUS TUF Gaming GeForce RTX 5090 32GB GDDR7 Graphics Cardused, asking price$6,450In stock4 h agoBuy
eBayPNY NVIDIA GeForce RTX 5090 OC 32GB GDDR7 PCIe 5.0 x16 Graphics Card excellentused, asking price$6,399+ $59 deliveryIn stock4 h agoBuy
eBayMSI GeForce RTX 5090 32GB VENTUS 3X OC GDDR7 Graphics Cardused, asking price$6,749In stock4 h agoBuy
eBayASUS TUF GeForce RTX 5090 Graphics Card 32GB VRAMused, asking price$6,700+ $50 deliveryIn stock47 min agoBuy
eBayPalit GeForce RTX 5090 GameRock 32GB GDDR7 PCI-Express Graphics Card-used, asking price$6,775In stock4 h agoBuy
eBayGigabyte AORUS GeForce RTX 5090 MASTER ICEused, asking price$6,900In stock4 h agoBuy
eBayGigabyte AORUS GeForce RTX 5090 Master 32GB GDDR7 GPU Video Cardused, asking price$6,949In stock4 h agoBuy
eBayMSI GeForce RTX 5090 SUPRIM LIQUID SOC 32GB GDDR7 PCI-E 5.0 Graphics Card GPUused, asking price$6,949In stock4 h agoBuy
eBayMSI GeForce RTX 5090 32GB GDDR7 VENTUS 3X OC Graphics Cardused, asking price$7,000+ $70 deliveryIn stock4 h agoBuy
eBayASUS TUF GeForce RTX 5090 32GB GDDR7 Gaming OC Edition PCIe 5.0 Graphics CardNew$7,199In stock47 min agoBuy
eBayNEW ASUS ProArt GeForce RTX 5090 32GB GDDR7 OC Edition Graphics Cardused, asking price$7,199In stock4 h agoBuy
eBayASUS ROG Astral RTX 5090 OC BTF Edition 32GB GDDR7New$7,399In stock47 min agoBuy
eBayGIGABYTE NVIDIA GeForce RTX 5090 GAMING OC 32GB GDDR7New$7,400In stock4 h agoBuy
eBayASUS TUF Gaming GeForce RTX 5090 32GB Gaming Graphics CardNew$7,400+ $30 deliveryIn stock47 min agoBuy
eBayASUS TUF GeForce RTX 5090 32GB GDDR7 Gaming OC Edition PCIe 5.0 Graphics CardNew$7,450+ $30 deliveryIn stock47 min agoBuy
eBayGIGABYTE AORUS RTX 5090 MASTER ICE OC 32GB White GV-N5090AORUSM ICE-32GDused, asking price$7,499In stock4 h agoBuy
eBayGigabyte AORUS RTX 5090 Infinity OC 32GB GDDR7 PCIe 5.0 Dual-Fan GPU NEW TESTEDNew$7,499In stock4 h agoBuy
eBayASUS TUF Gaming GeForce RTX 5090 32GB GDDR7 PCIe 5.0 HDMI/DPNew$7,500In stock4 h agoBuy
eBay🔥ASUS RTX 5090 TUF 32GB NVIDIA GeForce Graphics CardNew$7,500In stock4 h agoBuy
eBayASUS ROG Astral OC NVIDIA GeForce RTX 5090 32GB GDDR7New$7,500+ $40 deliveryIn stock4 h agoBuy
eBayGigabyte AORUS RTX 5090 Master ICE 32GB White GV-N5090AORUSM NewNew$7,600In stock4 h agoBuy
eBay🔥ASUS RTX 5090 TUF OC 32GB NVIDIA GeForce Graphics CardNew$7,640In stock4 h agoBuy
eBayUsed GeForce RTX 5090 on eBayused, asking price$7,688In stock5 h agoBuy
eBay🔥ASUS RTX 5090 ROG Astral OC 32GB NVIDIA GeForceNew$7,700In stock4 h agoBuy
AmazonMSI GeForce RTX 5090 32G SUPRIM SOCNew$8,000In stock2 h agoBuy
eBayNVIDIA RTX 5090 32GB 575W pulled from NEW DELL Alienware Area-51 0 HoursNew$8,395In stock4 h agoBuy
AmazonZOTAC Gaming Geforce RTX 5090 Amp Extreme Infinity Nvidia 32 GbNew$8,479In stock39 min agoBuy
AmazonASUS GeForce RTX 5090 Astral LC Overclocked Liquid Cooled 32GB GDDR7 PCIe 5.0…New$8,800+ $28 deliveryIn stock2 h agoBuy
AmazonGigabyte AORUS GeForce RTX 5090 Infinity 32G Graphics CardNew$9,000In stock39 min agoBuy
AmazonASUS TUF Gaming GeForce RTX 5090 Triple Fan GPUNew$9,300In stock39 min agoBuy
AmazonASUS ROG Astral GeForce RTX 5090 32GB GDDR7 White OC Edition Gaming Quad Fan…New$9,500In stock2 h agoBuy
AmazonMSI GeForce RTX 5090 32G Vanguard SOC Launch Edition Graphics Card VD8998New$9,979In stock2 h agoBuy
AmazonASUS ROG Astral GeForce RTX 5090 Edition 20 OC Quad-Fan Gaming Graphics CardNew$11,500In stock2 h agoBuy
eBayASUS ROG Astral GeForce RTX 5090 32GB GDDR7 NEW UNUSED Graphics Cardused, asking price$6,999Out of stock4 h agoBuy
eBayAORUS Master Ice NVIDIA GeForce RTX 5090 Graphics Cardused, asking price$7,000Out of stock4 h agoBuy
eBayNVIDIA GeForce RTX 5090 Founders Edition Graphics Cardused, asking price$7,000Out of stock4 h agoBuy
eBayNVIDIA GeForce RTX 5090 FE Founders Edition 32GB Graphics Cardused, asking price$7,250Out of stock4 h agoBuy
eBayASUS GeForce RTX 5090 ROG Astral OC Edition 32GB GDDR7- NEW/SEALEDNew$7,500Out of stock4 h agoBuy
eBayASUS TUF GeForce RTX 5090 32GB GDDR7 Gaming OC Edition PCIe 5.0 Graphics CardNew$7,599Out of stock4 h agoBuy

Used on eBay: median asking price $7,688, most between $7,000 and $9,000 (92 listings, 2026-10-30). Used price history

Price history

Lowest price shown each day over the last 90 days.

$4,773$6,095$7,4162026-10-142026-10-30
Lowest new priceLowest used asking price

What it runs

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

ModelQuantFitsMemoryMax contextDecode @32kPrefillGood for
Qwen 3.8 27B

Alibaba Qwen

Q8_0fits30.1 GB51k89k with q8 cache

35tok/sest.

1517 tok/schat, coding, agents
Qwen 3.6 27B

Alibaba Qwen

Q8_0fits29.7 GB57k100k with q8 cache

36tok/sest.

1517 tok/schat, coding, agents
Gemma 4 31B

Google

Q6_Kfits27.6 GB76k143k with q8 cache

39tok/sest.

1351 tok/schat, coding, agents
Qwen 3.6 35B-A3B

Alibaba Qwen

Q6_Kfits30.4 GB71k112k with q8 cache

201tok/sest.

10830 tok/schat, coding, agents, long documents
Qwen 3.5 27B

Alibaba Qwen

Q8_0fits29.7 GB57k100k with q8 cache

36tok/sest.

1517 tok/schat, coding, agents
Gemma 4 26B-A4B

Google

Q8_0fits26.7 GB216k256k with q8 cache

132tok/sest.

9635 tok/schat, coding, agents, long documents
Qwen 3.5 35B-A3B

Alibaba Qwen

Q6_Kfits28.4 GB148k232k with q8 cache

212tok/sest.

10830 tok/schat, coding, agents, long documents
GLM 4.7 Flash

Z.ai

Q6_Kfits25.5 GB133k198k with q8 cache

114tok/sest.

5654 tok/schat, coding, agents, long documents
Devstral Small 2 24B

Mistral AI

Q8_0fits29.2 GB45k82k with q8 cache

37tok/sest.

1601 tok/schat, coding, agents
Nemotron 3.5 Lightning 30B-A3B

NVIDIA

UD-Q5_K_Mfits29.3 GB214k256k with q8 cache

214tok/sest.

12358 tok/schat, coding, agents, long documents
Kimi Linear 48B-A3B

Moonshot AI

Q4_K_Mfits29.2 GB196k267k with q8 cache

311tok/sest.

9333 tok/schat, coding, long documents
gpt-oss 20B

OpenAI

MXFP4fits12.9 GB128k

206tok/sest.

8085 tok/schat, coding, agents, long documents
Qwen3 Coder 30B-A3B

Alibaba Qwen

Q6_Kfits27.3 GB73k131k with q8 cache

117tok/sest.

4980 tok/schat, coding, agents
Qwen3 32B

Alibaba Qwen

Q5_K_Mfits30.5 GB35k40k with q8 cache

35tok/sest.

942 tok/schat, coding
Gemma 4 12B

Google

Q8_0fits13.5 GB256k

82tok/sest.

3518 tok/schat, coding, long documents
Qwen 3.5 9B

Alibaba Qwen

Q8_0fits10.8 GB256k

104tok/sest.

4384 tok/schat, coding, long documents
Mistral Small 3.2 24B

Mistral AI

Q8_0fits29.2 GB45k82k with q8 cache

37tok/sest.

1601 tok/schat, coding
DeepSeek R1 Distill Qwen 32B

DeepSeek

Q5_K_Mfits30.6 GB35k65k with q8 cache

35tok/sest.

1081 tok/schat, coding
Gemma 3 27B

Google

Q8_0fits30.5 GB42k79k with q8 cache

35tok/sest.

1610 tok/schat, coding
Ministral 3 14B

Mistral AI

Q8_0fits19.3 GB106k194k with q8 cache

56tok/sest.

2435 tok/schat, coding
Qwen3 14B

Alibaba Qwen

Q8_0fits20.5 GB40k

53tok/sest.

2189 tok/schat, coding
DeepSeek R1 0528 Qwen3 8B

DeepSeek

Q8_0fits13.5 GB128k

82tok/sest.

3611 tok/schat, coding, long documents
Qwen3 8B

Alibaba Qwen

Q8_0fits13.5 GB40k

82tok/sest.

3611 tok/schat, coding, long documents
Phi-4 14B

Microsoft

Q8_0fits21.6 GB16k

50tok/sest.

2201 tok/schat, coding
Qwen 3.5 4B

Alibaba Qwen

Q8_0fits6.1 GB256k

198tok/sest.

8202 tok/schat, coding, long documents
Ministral 3 8B

Mistral AI

Q8_0fits13.5 GB160k256k with q8 cache

82tok/sest.

3488 tok/schat, coding, long documents
Granite 4.2 8B

IBM

Q8_0fits14.6 GB128k

76tok/sest.

3321 tok/schat, coding, agents, long documents
Gemma 4 E4B

Google

Q8_0fits9.4 GB128k

121tok/sest.

5507 tok/schat, coding, long documents
LFM2.5 8B-A1B

Liquid AI

Q8_0fits10.8 GB125k

249tok/sest.

18013 tok/schat, coding, long documents
Llama 3.1 8B

Meta

Q6_Kfits11.0 GB128k

102tok/sest.

3815 tok/schat, coding, long documents
Qwen2.5 0.5B

Alibaba Qwen

Q8_0fits1.8 GB32k

1190tok/sest.

39231 tok/schat, coding, long documents
Qwen3.5 0.8B

Alibaba Qwen

Q8_0fits2.0 GB256k

901tok/sest.

36851 tok/schat, coding, agents, long documents
Qwen3.5 2B

Alibaba Qwen

Q5_K_Mfits2.6 GB256k

598tok/sest.

17568 tok/schat, coding, agents, long documents
LFM3 1.7B

Liquid AI

Q8_0fits3.0 GB256k

492tok/sest.

21869 tok/schat, coding, agents, long documents
DeepSeek R1 Distill Qwen 1.5B

DeepSeek

Q8_0fits3.5 GB128k

392tok/sest.

14758 tok/schat, coding, long documents
MiniCPM5 2B

openbmb

Q8_0fits4.7 GB128k

272tok/sest.

8814 tok/schat, coding, agents, long documents
Spark X2.5 4B

XHToken

mlx-4bitfits4.9 GB678k1024k with q8 cache

258tok/sest.

8655 tok/schat, coding, agents, long documents
LFM2.5 2.6B

Liquid AI

Q8_0fits5.4 GB128k

227tok/sest.

9983 tok/schat, coding, agents, long documents
LFM2.5 VL 3B

Liquid AI

Q8_0fits5.4 GB32k

227tok/sest.

9155 tok/schat, coding, agents, long documents
Mellum2.1 12B A2.5B Thinking

JetBrains

Q8_0fits13.4 GB128k

210tok/sest.

13006 tok/schat, coding, agents, long documents
FrogNano 4B 2609

Microsoft

Q8_0fits6.2 GB256k

193tok/sest.

8202 tok/schat, coding, agents, long documents
granite vision 4.1 4b

IBM

Q8_0fits6.8 GB128k

176tok/sest.

6396 tok/schat, coding, long documents
granite 4.2 3b

IBM

Q8_0fits7.0 GB128k

169tok/sest.

6703 tok/schat, coding, agents, long documents
Kimi VL A3B Thinking 2506

Moonshot AI

Q8_0fits17.6 GB128k

162tok/sest.

9773 tok/schat, coding, long documents
Kimi VL A3B

Moonshot AI

mlx-8bitfits18.4 GB128k

156tok/sest.

8224 tok/schat, coding, agents, long documents
Ministral 3 3B Instruct 2512

Mistral AI

Q8_0fits7.5 GB254k256k with q8 cache

156tok/sest.

6408 tok/schat, coding, agents, long documents
LFM2.5 24B A2B

Liquid AI

Q8_0fits27.1 GB82k128k with q8 cache

139tok/sest.

10039 tok/schat, coding, agents, long documents
GLM 4 9B 0414

Z.ai

mlx-5bitfits9.8 GB32k

116tok/sest.

3184 tok/schat, coding, agents, long documents
DeepSeek R1 Distill Qwen 7B

DeepSeek

Q8_0fits10.2 GB128k

111tok/sest.

4313 tok/schat, coding, long documents
GLM 4.6V Flash

Z.ai

Q8_0fits11.5 GB128k

98tok/sest.

3003 tok/schat, coding, agents, long documents
DeepSeek R1 Distill Llama 8B

DeepSeek

Q8_0fits12.8 GB128k

87tok/sest.

3815 tok/schat, coding, long documents
GLM 4.1V 9B Thinking

Z.ai

mlx-8bitfits13.1 GB64k

85tok/sest.

3003 tok/schat, coding, long documents
Ministral 3 8B Reasoning 2512

Mistral AI

Q8_0fits13.5 GB160k256k with q8 cache

82tok/sest.

3488 tok/schat, coding, agents, long documents
Ministral 3 14B Reasoning 2512

Mistral AI

Q8_0fits19.3 GB106k194k with q8 cache

56tok/sest.

2435 tok/schat, coding, agents
DeepSeek R1 Distill Qwen 14B

DeepSeek

Q8_0fits21.5 GB83k128k with q8 cache

50tok/sest.

2060 tok/schat, coding
Qwen3.8 27B OBLITERATED

OBLITERATUS

mlx-4bitfits22.3 GB165k256k with q8 cache

48tok/sest.

1517 tok/schat, coding, agents, long documents
Muse Glimmer 30B

meta-models

Q6_Kfits23.2 GB128k

46tok/sest.

1462 tok/schat, coding, agents, long documents
granite 4.2 30b

IBM

Q5_K_Mfits28.5 GB43k80k with q8 cache

38tok/sest.

1242 tok/schat, coding, agents
Devstral Small 2507

Mistral AI

Q8_0fits29.2 GB45k82k with q8 cache

37tok/sest.

1625 tok/schat, coding, agents
Magistral Small 2506

Mistral AI

Q8_0fits29.2 GB40k

37tok/sest.

1625 tok/schat, coding
Magistral Small 2507

Mistral AI

Q8_0fits29.2 GB40k

37tok/sest.

1625 tok/schat, coding, agents
Magistral Small 2509

Mistral AI

Q8_0fits29.2 GB45k82k with q8 cache

37tok/sest.

1601 tok/schat, coding, agents
Qwen 3.5 122B-A10B

Alibaba Qwen

UD-Q2_K_XLoffload40.7 GB–

28tok/sest.

3056 tok/schat, coding
Qwen3 Coder Next

Alibaba Qwen

Q4_K_Moffload46.9 GB–

27tok/sest.

6840 tok/schat, coding
Nemotron 3 Super 120B-A12B

NVIDIA

UD-Q2_K_XLoffload52.2 GB–

13tok/sest.

2722 tok/s–
Mistral Small 4 119B

Mistral AI

UD-Q2_K_XLoffload39.0 GB–

43tok/sest.

3480 tok/schat, coding, agents, long documents
GLM 4.5 Air

Z.ai

Q2_Koffload48.8 GB–

7tok/sest.

1148 tok/s–
Qwen3 Next 80B-A3B

Alibaba Qwen

Q4_K_Moffload46.9 GB–

33tok/sest.

8139 tok/schat, coding, agents, long documents
Llama 3.3 70B

Meta

Q4_K_Moffload50.5 GB–

2tok/sest.

393 tok/s–
DeepSeek R1 Distill Llama 70B

DeepSeek

Q4_K_Moffload50.5 GB–

2tok/sest.

393 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––––
gpt-oss 120B

OpenAI

Q4_K_Mwon't run60.5 GB––––
DeepSeek R1

DeepSeek

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

DeepSeek

Q4_K_Mwon't run380.2 GB––––
DeepSeek R1 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 5090
Memory
32 GB GDDR7
Memory bus
512-bit
Memory bandwidth
1,792 GB/s
FP16 compute
209 TFLOPS
Software
CUDA
Board power
575 W
PCIe generation
Gen 5
PCIe lanes
x16
Parts in our builds with it
AMD Ryzen 9 9950X, MSI MPG X870E Carbon WiFi, Lian Li O11 Dynamic EVO, Seasonic Vertex GX-1200 1200W, Kingston Fury Beast 96GB (2×48GB) DDR5-6400, WD Black SN850X 4TB

Compare with

Questions

How much memory does the NVIDIA GeForce RTX 5090 have for AI models?
The NVIDIA GeForce RTX 5090 has 32 GB of GDDR7 memory with 1,792 GB/s of bandwidth, which sets how fast it generates text.
What is the best model the NVIDIA GeForce RTX 5090 can run locally?
Qwen 3.8 27B (Q8_0) fits fully in its memory at 32k context and generates at about 35 tok/s, an estimate from its memory bandwidth. 62 of the 128 models we track fit at that context.
Can the NVIDIA GeForce RTX 5090 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 5090 and system RAM can hold.
How much does the NVIDIA GeForce RTX 5090 cost in the US?
The best new price for the NVIDIA GeForce RTX 5090 in the US is $4,921 at eBay; used, it starts at $6,450 (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