buyaigear
Prices checked 8 min ago

NVIDIA · Blackwell · 96 GB · Qwen3.8 27B · Q4_K_M: ~71 tok/s

NVIDIA RTX PRO 6000 Blackwell

The most memory you can put on one PCIe card: 96 GB of GDDR7 with ECC and 1.8 TB/s of bandwidth. Enough for a 70B model at Q8, or a 120B mixture-of-experts model at Q4 with context to spare. Sold as Workstation Edition (600 W), Max-Q (300 W) and Server Edition.

Lowest price right now

$16,499

eBay · free shipping · $171 per GB · observed 2026-10-14 22:18 UTC

See it on eBaySee it on Amazon

Where to buy

VendorPriceConditionObserved
eBay
cheapest active listing		 $16,499
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

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

All 76 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+~92~7,400
Gemma 4 31B Mar 2026Q8_035 GBfits128K+~36~2,900
Gemma 4 26B-A4B Mar 2026Q8_028 GBfits128K+~290~23,000
Gemma 3 27B Mar 2025Q8_031 GBfits128K+~40~3,200
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 2025Q6_K90 GBfits39K~120~7,300
gpt-oss
gpt-oss-120b Aug 2025Q5_K_M85 GBfits128K+~320~17,000
gpt-oss-20b Aug 2025Q8_024 GBfits128K+~310~24,000
Llama
Llama 4 Scout 109B-A17B Apr 2025Q6_K92 GBfits25K~84~5,200
Llama 3.3 70B Dec 2024Q8_079 GBfits58K~16~1,200
Llama 3.1 8B Jul 2024Q8_011 GBfits128K+~140~11,000
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 2026Q5_K_M95 GBfits9K~13~690
Mistral Small 4 119B-A6.5B Mar 2026Q5_K_M91 GBfits16K~250~14,000
Mistral Small 3.2 24B Jun 2025Q8_028 GBfits128K+~46~3,700
Qwen
Qwen3.8 Flash-Next 125B-A6B Aug 2026Q5_K_M90 GBfits128K+~270~15,000
Qwen3.8 27B Aug 2026 (your pick)Q8_031 GBfits128K+~41~3,300
Qwen3.6 27B Apr 2026Q8_031 GBfits128K+~41~3,300
Qwen3.6 35B-A3B Apr 2026Q8_039 GBfits128K+~370~29,000
Qwen3 Coder 480B-A35B Jul 2025Q4_K_M296 GBdoes not fit
Qwen3 235B-A22B Jul 2025IQ2_M83 GBfits74K~160~4,000
Qwen3 32B Apr 2025Q8_038 GBfits128K+~34~2,700

Specifications

Memory
96 GB GDDR7 ECC
Memory bandwidth
1,792 GB/s
Bus width
512-bit
Shader cores
24,064
Tensor cores
752
FP32
125.0 TFLOPS
FP16 (dense)
504 TFLOPS
FP8 (dense)
1008 TFLOPS
Power
600 W
Form factor
Dual slot, full height (Workstation Edition)
Interface
PCIe 5.0 x16
Architecture
Blackwell
Launched
2025
MSRP
$8,565

Source: manufacturer specifications.