buyaigear
Prices checked 7 min ago Sign in

NVIDIA · Ada Lovelace · 16 GB · Qwen3.8 27B · Q4_K_M at 8K context: ~11 tok/s with RAM offload

NVIDIA GeForce RTX 4080 16GB

16 GB of Ada at 717 GB/s with FP8 tensor cores: a 14B model at Q6 or a 24B at Q4 at a good clip. Used prices fell when the 50 series arrived; the 4080 Super is the same card with a little more of everything.

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

Lowest price right now

$1,099

eBay · free shipping · $68 per GB · observed 2026-11-14 18:37 UTC

Buy the cheapest on eBay, $1,099

free shipping · Used · leahwenzel14 230 · 100.0%

See more on eBay

Or rent one from $0.25 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.

$938$996$1,053$1,111Nov 9Nov 14lowest $949.99

Where to buy

VendorPriceConditionObserved
eBay
cheapest active listing		 $1,099
free shipping		 new and used 2026-11-14 18:37 UTC Go to eBay

On eBay now

24 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 24 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 4080 in the cloud right now, checked every hour.

CloudPer hourListed asAvailable
Vast.ai$0.25RTX 40806 verified offersRent on Vast.ai

At $0.25 an hour on Vast.ai, the $1,099 a used one costs on eBay buys about 4,500 hours of rental: 6 months around the clock, or 18 months 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 GBfits109K~36~35~1,400
Gemma 4 31B Mar 2026IQ2_M13 GBfits48K~42~36~560
Gemma 4 26B-A4B Mar 2026Q3_K_M14 GBfits102K~130~110~4,500
Gemma 3 27B Mar 2025Q3_K_M16 GBfits12K~33~620
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 52 GB in system RAM~6.5~710
gpt-oss
gpt-oss-120b Aug 2025Q3_K_M59 GBruns with 44 GB in system RAM~19~17~1,700
gpt-oss-20b Aug 2025Q4_K_M15 GBfits33K~110~86~4,700
Llama
Llama 4 Scout 109B-A17B Apr 2025Q4_K_M70 GBruns with 54 GB in system RAM~4.6~500
Llama 3.3 70B Dec 2024Q4_K_M47 GBruns with 32 GB in system RAM~1.2~1.0~120
Llama 3.1 8B Jul 2024Q8_011 GBfits44K~49~36~2,100
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 2026Q3_K_M67 GBruns with 52 GB in system RAM~0.8~67
Mistral Small 4 119B-A6.5B Mar 2026Q3_K_M65 GBruns with 49 GB in system RAM~12~1,300
Mistral Small 3.2 24B Jun 2025Q3_K_M15 GBfits16K~36~710
Nemotron
Nemotron 3.5 Lightning 30B-A3B Aug 2026IQ2_M12 GBfits128K+~160~150~4,900
Qwen
Qwen3.8 Flash-Next 125B-A6B Aug 2026Q3_K_M63 GBruns with 47 GB in system RAM~16~16~1,400
Qwen3.8 27B Aug 2026 (your pick)Q3_K_M15 GBfits18K~34~630
Qwen3.6 27B Apr 2026Q3_K_M15 GBfits18K~34~630
Qwen3.6 35B-A3B Apr 2026IQ2_M14 GBfits123K~170~140~5,700
Qwen3.5 9B Feb 2026Q8_011 GBfits128K+~48~44~1,900
Qwen3 Coder 480B-A35B Jul 2025Q4_K_M296 GBdoes not fit
Qwen3 235B-A22B Jul 2025Q4_K_M146 GBdoes not fit
Qwen3 32B Apr 2025IQ2_M15 GBfits12K~35~520

Specifications

Memory
16 GB GDDR6X
Memory bandwidth
717 GB/s
Bus width
256-bit
Shader cores
9,728
Tensor cores
304
FP32
48.7 TFLOPS
FP16 (dense)
98 TFLOPS
FP8 (dense)
195 TFLOPS
Power
320 W
Form factor
Triple slot, full height
Interface
PCIe 4.0 x16
Architecture
Ada Lovelace
Launched
2022
MSRP
$1,199

Source: manufacturer specifications.

Embed the live price

A badge that always shows the current eBay low for the RTX 4080, delivered, and links back here. Free to use in a README, a forum signature or a blog post.

RTX 4080: live eBay low

HTML and Markdown snippets 
<a href="https://buyaigear.com/gpus/rtx-4080-16gb"><img src="https://buyaigear.com/badge/rtx-4080-16gb.svg" alt="RTX 4080: live eBay low" height="20"></a>
[![RTX 4080: live eBay low](https://buyaigear.com/badge/rtx-4080-16gb.svg)](https://buyaigear.com/gpus/rtx-4080-16gb)