buyaigear
Prices checked 6 min ago

NVIDIA · Ada Lovelace · 48 GB · Qwen3.8 27B · Q4_K_M: ~38 tok/s

NVIDIA RTX 6000 Ada

The previous generation's 48 GB workstation card, now the used-market way to run a 70B model at Q4 on one 300 W GPU.

Lowest price right now

$7,499.99

eBay · free shipping · $156 per GB · observed 2026-10-14 22:18 UTC

See it on eBaySee it on Amazon

Where to buy

VendorPriceConditionObserved
eBay
cheapest active listing		 $7,499.99
free shipping		 new and used 2026-10-14 22:18 UTC Go to eBay
Amazon
price tracking coming		 price on Amazon new Go to Amazon

On eBay now

19 listings passed our filters at the last check. Cheapest delivered first. Seller reputation is feedback count and positive rate.

All 19 listings · Open the search on eBay

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. The model you picked on the ladder is highlighted. Estimates from the spec sheet, not measurements: see how we estimate.

ModelQuantNeeds at 8KFitMax contextDecode tok/sPrefill 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+~49~2,700
Gemma 4 31B Mar 2026Q8_035 GBfits128K+~19~1,000
Gemma 4 26B-A4B Mar 2026Q8_028 GBfits128K+~150~8,400
Gemma 3 27B Mar 2025Q8_031 GBfits128K+~21~1,200
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 2025IQ2_M39 GBfits54K~150~2,700
gpt-oss
gpt-oss-120b Aug 2025IQ2_M42 GBfits89K~360~6,200
gpt-oss-20b Aug 2025Q8_024 GBfits128K+~160~8,800
Llama
Llama 4 Scout 109B-A17B Apr 2025IQ2_M40 GBfits46K~110~1,900
Llama 3.3 70B Dec 2024Q4_K_M47 GBfits10K~14~450
Llama 3.1 8B Jul 2024Q8_011 GBfits128K+~74~4,000
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 2026IQ2_M48 GBfits8K~14~250
Mistral Small 4 119B-A6.5B Mar 2026IQ2_M47 GBfits10K~280~4,900
Mistral Small 3.2 24B Jun 2025Q8_028 GBfits125K~25~1,300
Qwen
Qwen3.8 Flash-Next 125B-A6B Aug 2026IQ2_M44 GBfits128K+~310~5,300
Qwen3.8 27B Aug 2026 (your pick)Q8_031 GBfits128K+~22~1,200
Qwen3.6 27B Apr 2026Q8_031 GBfits128K+~22~1,200
Qwen3.6 35B-A3B Apr 2026Q8_039 GBfits128K+~200~11,000
Qwen3 Coder 480B-A35B Jul 2025Q4_K_M296 GBdoes not fit
Qwen3 235B-A22B Jul 2025Q4_K_M146 GBdoes not fit
Qwen3 32B Apr 2025Q8_038 GBfits43K~18~970

Specifications

Memory
48 GB GDDR6 ECC
Memory bandwidth
960 GB/s
Bus width
384-bit
Shader cores
18,176
Tensor cores
568
FP32
91.1 TFLOPS
FP16 (dense)
182 TFLOPS
FP8 (dense)
364 TFLOPS
Power
300 W
Form factor
Dual slot, full height
Interface
PCIe 4.0 x16
Architecture
Ada Lovelace
Launched
2022
MSRP
$6,800

Source: manufacturer specifications.