buyaigear
Prices checked 8 min ago

NVIDIA · Ampere · 80 GB · Qwen3.8 27B · Q4_K_M: ~76 tok/s

NVIDIA A100 80GB PCIe

80 GB of HBM2e at 1.9 TB/s on a passively cooled data-center card. A 70B model at Q8 fits. It needs a chassis that pushes air through it, or a bolt-on fan.

Lowest price right now

$15,299

eBay · free shipping · $191 per GB · observed 2026-10-14 22:19 UTC

See it on eBaySee it on Amazon

Where to buy

VendorPriceConditionObserved
eBay
cheapest active listing		 $15,299
free shipping		 new and used 2026-10-14 22:19 UTC Go to eBay
Amazon
price tracking coming		 price on Amazon new Go to Amazon

On eBay now

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

All 26 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+~99~4,600
Gemma 4 31B Mar 2026Q8_035 GBfits128K+~39~1,800
Gemma 4 26B-A4B Mar 2026Q8_028 GBfits128K+~310~14,000
Gemma 3 27B Mar 2025Q8_031 GBfits128K+~43~2,000
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 2025Q5_K_M78 GBfits16K~150~4,500
gpt-oss
gpt-oss-120b Aug 2025Q4_K_M73 GBfits96K~400~11,000
gpt-oss-20b Aug 2025Q8_024 GBfits128K+~330~15,000
Llama
Llama 4 Scout 109B-A17B Apr 2025Q4_K_M70 GBfits59K~120~3,200
Llama 3.3 70B Dec 2024Q8_079 GBfits10K~17~770
Llama 3.1 8B Jul 2024Q8_011 GBfits128K+~150~6,800
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 GBfits42K~20~430
Mistral Small 4 119B-A6.5B Mar 2026Q4_K_M79 GBfits9K~320~8,400
Mistral Small 3.2 24B Jun 2025Q8_028 GBfits128K+~49~2,300
Qwen
Qwen3.8 Flash-Next 125B-A6B Aug 2026Q4_K_M78 GBfits89K~340~9,100
Qwen3.8 27B Aug 2026 (your pick)Q8_031 GBfits128K+~44~2,000
Qwen3.6 27B Apr 2026Q8_031 GBfits128K+~44~2,000
Qwen3.6 35B-A3B Apr 2026Q8_039 GBfits128K+~400~18,000
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 GBfits128K+~36~1,700

Specifications

Memory
80 GB HBM2e
Memory bandwidth
1,935 GB/s
Bus width
5120-bit
Shader cores
6,912
Tensor cores
432
FP32
19.5 TFLOPS
FP16 (dense)
312 TFLOPS
Power
300 W
Form factor
Dual slot, passive, needs chassis airflow
Interface
PCIe 4.0 x16
Architecture
Ampere
Launched
2021

Source: manufacturer specifications.