buyaigear
Prices checked 7 min ago Sign in

NVIDIA · Volta · 16 GB · Qwen3.8 27B · Q4_K_M at 8K context: ~12 tok/s with RAM offload

NVIDIA Tesla V100 16GB PCIe

The PCIe card version of the 16 GB V100: 900 GB/s of HBM2 and tensor cores for a few hundred dollars, with no adapter board to buy. Passive, so it needs a fan shroud, and CUDA 13 dropped Volta, so stay on CUDA 12 builds.

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

Lowest price right now

$302.95

eBay · $289 + $13.95 shipping · $18 per GB · observed 2026-11-14 18:37 UTC

Buy the cheapest on eBay, $302.95

$289 + $13.95 shipping · Used · rtone-32 995 · 100.0%

See more on eBay

Or rent one from $0.14 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.

$299$301$302$304Nov 9Nov 14lowest $300

Where to buy

VendorPriceConditionObserved
eBay
cheapest active listing		 $302.95
$289 + $13.95 shipping		 new and used 2026-11-14 18:37 UTC Go to eBay

On eBay now

81 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 81 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 Tesla V100 16GB in the cloud right now, checked every hour.

CloudPer hourListed asAvailable
Vast.ai$0.14Tesla V1001 verified offerRent on Vast.ai

At $0.14 an hour on Vast.ai, the $302.95 a used one costs on eBay buys about 2,100 hours of rental: 3 months around the clock, or 9 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~46~44~1,600
Gemma 4 31B Mar 2026IQ2_M13 GBfits48K~53~45~640
Gemma 4 26B-A4B Mar 2026Q3_K_M14 GBfits102K~140~130~5,200
Gemma 3 27B Mar 2025Q3_K_M16 GBfits12K~41~720
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~6.5~820
gpt-oss
gpt-oss-120b Aug 2025Q3_K_M59 GBruns with 44 GB in system RAM~19~18~1,900
gpt-oss-20b Aug 2025Q4_K_M15 GBfits33K~130~100~5,400
Llama
Llama 4 Scout 109B-A17B Apr 2025Q4_K_M70 GBruns with 54 GB in system RAM~4.6~580
Llama 3.3 70B Dec 2024Q4_K_M47 GBruns with 32 GB in system RAM~1.3~1.0~140
Llama 3.1 8B Jul 2024Q8_011 GBfits44K~61~46~2,400
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~0.8~77
Mistral Small 4 119B-A6.5B Mar 2026Q3_K_M65 GBruns with 49 GB in system RAM~13~1,500
Mistral Small 3.2 24B Jun 2025Q3_K_M15 GBfits16K~45~820
Nemotron
Nemotron 3.5 Lightning 30B-A3B Aug 2026IQ2_M12 GBfits128K+~180~170~5,600
Qwen
Qwen3.8 Flash-Next 125B-A6B Aug 2026Q3_K_M63 GBruns with 47 GB in system RAM~17~16~1,600
Qwen3.8 27B Aug 2026 (your pick)Q3_K_M15 GBfits18K~42~730
Qwen3.6 27B Apr 2026Q3_K_M15 GBfits18K~42~730
Qwen3.6 35B-A3B Apr 2026IQ2_M14 GBfits123K~180~160~6,500
Qwen3.5 9B Feb 2026Q8_011 GBfits128K+~60~55~2,200
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~44~600

Specifications

Memory
16 GB HBM2
Memory bandwidth
900 GB/s
Bus width
4096-bit
Shader cores
5,120
Tensor cores
640
FP32
14.0 TFLOPS
FP16 (dense)
112 TFLOPS
Power
250 W
Form factor
Dual slot, passive, needs a fan
Interface
PCIe 3.0 x16
Architecture
Volta
Launched
2017

Source: manufacturer specifications.

Embed the live price

A badge that always shows the current eBay low for the Tesla V100 16GB, delivered, and links back here. Free to use in a README, a forum signature or a blog post.

Tesla V100 16GB: live eBay low

HTML and Markdown snippets 
<a href="https://buyaigear.com/gpus/tesla-v100-16gb-pcie"><img src="https://buyaigear.com/badge/tesla-v100-16gb-pcie.svg" alt="Tesla V100 16GB: live eBay low" height="20"></a>
[![Tesla V100 16GB: live eBay low](https://buyaigear.com/badge/tesla-v100-16gb-pcie.svg)](https://buyaigear.com/gpus/tesla-v100-16gb-pcie)