buyaigear
Prices checked 7 min ago Sign in

NVIDIA · Blackwell · 32 GB · Qwen3.8 27B · Q4_K_M at 8K context: ~68 tok/s

NVIDIA GeForce RTX 5090 Founders Edition

NVIDIA's own two-slot card at the $1,999 list price, the one everyone hunts: the same chip and 32 GB as every other 5090 in a cooler that fits where partner cards do not. Scarce at list; the prices here are what sellers ask.

Watch Qwen3.8 27B stream at this machine's speed

Lowest price right now

$6,265.89

eBay · $6,250 + $15.89 shipping · $195 per GB · observed 2026-11-14 18:37 UTC

Buy the cheapest on eBay, $6,265.89

$6,250 + $15.89 shipping · Used · ghostofvet 44 · 100.0%

See more on eBay

Or rent one from $0.46 an hour

Price alert

One email per move, item plus shipping. Clear the price to hear about any drop. Manage alerts.

Price history

Daily low across every tracked vendor, last 6 days.

$5,744$6,015$6,285$6,556Nov 9Nov 14lowest $5,799.95

Where to buy

VendorPriceConditionObserved
eBay
cheapest active listing		 $6,265.89
$6,250 + $15.89 shipping		 new and used 2026-11-14 18:37 UTC Go to eBay

On eBay now

97 listings passed our filters at the last check, 7 min ago. We check every 28 minutes. Cheapest delivered first. Seller reputation is feedback count and positive rate.

All 97 listings · Open the search on eBay

Rent one by the hour

Try it before you buy, or skip buying: the cheapest on-demand price for one RTX 5090 FE in the cloud right now, checked every hour.

CloudPer hourListed asAvailable
Vast.ai$0.46RTX 509042 verified offersRent on Vast.ai
Runpod$0.69RTX 5090stock: lowRent on Runpod

At $0.46 an hour on Vast.ai, the $6,265.89 a used one costs on eBay buys about 14,000 hours of rental: 19 months around the clock, or 4.8 years at 8 hours a day. Use it more than that and buying comes out ahead; your power bill pushes that point later, resale value pulls it earlier.

Rental prices for every card · Rental links are referral links: we earn a small share of what you spend, at no cost to you.

What it runs

For each model, grouped by vendor with the newest first: the largest quant that fits with 8K of context and the estimated speed for one user, at 8K and at 32K of context. On a card, a model too big for its memory can still run with part of the weights in system RAM; we assume 64 GB, and the speed shown accounts for it. The model you picked on the ladder is highlighted. Estimates from the spec sheet, not measurements: see how we estimate.

ModelQuantNeeds at 8KFitMax contextDecode at 8KAt 32KPrefill tok/s
DeepSeek
DeepSeek V4.1 Flash 552B-A16B Sep 2026Q4_K_M338 GBdoes not fit
DeepSeek V4 Flash 284B-A13B Jul 2026Q4_K_M175 GBdoes not fit
DeepSeek V3.1 671B-A37B Aug 2025Q4_K_M411 GBdoes not fit
Gemma
Gemma 4 12B May 2026Q8_014 GBfits128K+~91~88~3,100
Gemma 4 31B Mar 2026Q6_K27 GBfits63K~45~42~1,200
Gemma 4 26B-A4B Mar 2026Q8_028 GBfits128K+~140~130~9,700
Gemma 3 27B Mar 2025Q8_031 GBfits17K~39~1,300
GLM
GLM-5.3 753B-A40B Aug 2026Q4_K_M462 GBdoes not fit
GLM-5.3 Flash 320B-A18B Aug 2026Q4_K_M197 GBdoes not fit
GLM-4.6 355B-A32B Sep 2025Q4_K_M221 GBdoes not fit
GLM-4.5 Air 106B-A12B Jul 2025Q4_K_M68 GBruns with 36 GB in system RAM~9.3~8.1~1,500
gpt-oss
gpt-oss-120b Aug 2025Q4_K_M73 GBruns with 42 GB in system RAM~20~19~3,600
gpt-oss-20b Aug 2025Q8_024 GBfits128K+~140~120~10,000
Llama
Llama 4 Scout 109B-A17B Apr 2025Q4_K_M70 GBruns with 38 GB in system RAM~6.5~5.7~1,100
Llama 3.3 70B Dec 2024IQ2_M28 GBfits19K~44~520
Llama 3.1 8B Jul 2024Q8_011 GBfits128K+~120~91~4,600
MiMo
MiMo V2.6 Pro 1.02T-A42B Sep 2026Q4_K_M624 GBdoes not fit
MiMo V2.6 Flash 309B-A15B Sep 2026Q4_K_M190 GBdoes not fit
Mistral
Mistral Medium 3.5 128B Mar 2026Q4_K_M83 GBruns with 51 GB in system RAM~0.8~140
Mistral Small 4 119B-A6.5B Mar 2026Q4_K_M79 GBruns with 47 GB in system RAM~14~2,800
Mistral Small 3.2 24B Jun 2025Q8_028 GBfits30K~43~1,500
Nemotron
Nemotron 3.5 Lightning 30B-A3B Aug 2026Q6_K27 GBfits128K+~170~160~11,000
Qwen
Qwen3.8 Flash-Next 125B-A6B Aug 2026Q4_K_M78 GBruns with 46 GB in system RAM~17~17~3,100
Qwen3.8 27B Aug 2026 (your pick)Q8_031 GBfits28K~40~1,400
Qwen3.6 27B Apr 2026Q8_031 GBfits28K~40~1,400
Qwen3.6 35B-A3B Apr 2026Q6_K30 GBfits85K~170~160~12,000
Qwen3.5 9B Feb 2026Q8_011 GBfits128K+~120~110~4,100
Qwen3 Coder 480B-A35B Jul 2025Q4_K_M296 GBdoes not fit
Qwen3 235B-A22B Jul 2025IQ2_M83 GBruns with 51 GB in system RAM~8.0~7.2~840
Qwen3 32B Apr 2025Q6_K31 GBfits13K~40~1,100

Specifications

Memory
32 GB GDDR7
Memory bandwidth
1,792 GB/s
Bus width
512-bit
Shader cores
21,760
Tensor cores
680
FP32
104.8 TFLOPS
FP16 (dense)
210 TFLOPS
FP8 (dense)
419 TFLOPS
Power
575 W
Form factor
Dual slot, NVIDIA's own two-slot design
Interface
PCIe 5.0 x16
Architecture
Blackwell
Launched
2025
MSRP
$1,999

Source: manufacturer specifications.

Embed the live price

A badge that always shows the current eBay low for the RTX 5090 FE, delivered, and links back here. Free to use in a README, a forum signature or a blog post.

RTX 5090 FE: live eBay low

HTML and Markdown snippets 
<a href="https://buyaigear.com/gpus/rtx-5090-fe"><img src="https://buyaigear.com/badge/rtx-5090-fe.svg" alt="RTX 5090 FE: live eBay low" height="20"></a>
[![RTX 5090 FE: live eBay low](https://buyaigear.com/badge/rtx-5090-fe.svg)](https://buyaigear.com/gpus/rtx-5090-fe)