buyaigear
Prices checked 11 min ago

NVIDIA · Pascal · 16 GB · Qwen3.8 27B · Q4_K_M: does not fit

NVIDIA Tesla P100 16GB

HBM2 bandwidth from 2016 for pocket change. Faster per token than a P40 and it does real FP16, but only 16 GB and no tensor cores, and newer software is dropping Pascal.

Lowest price right now

$127.63

eBay · free shipping · $7 per GB · observed 2026-10-15 11:51 UTC

Buy the cheapest on eBay, $127.63

free shipping · Used · plc_pro_1847.0302 7,336 · 99.9%

All 145 listings on eBay

Compare: vs Instinct MI50 16GBvs Tesla P40

Where to buy

VendorPriceConditionObserved
eBay
cheapest active listing		 $127.63
free shipping		 new and used 2026-10-15 11:51 UTC Go to eBay

On eBay now

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

All 145 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 GBfits109K~38~270
Gemma 4 31B Mar 2026IQ2_M13 GBfits48K~46~110
Gemma 4 26B-A4B Mar 2026Q3_K_M14 GBfits102K~260~860
Gemma 3 27B Mar 2025Q3_K_M16 GBfits12K~35~120
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 GBdoes not fit
gpt-oss
gpt-oss-120b Aug 2025Q4_K_M73 GBdoes not fit
gpt-oss-20b Aug 2025Q4_K_M15 GBfits33K~220~910
Llama
Llama 4 Scout 109B-A17B Apr 2025Q4_K_M70 GBdoes not fit
Llama 3.3 70B Dec 2024Q4_K_M47 GBdoes not fit
Llama 3.1 8B Jul 2024Q8_011 GBfits44K~56~410
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 2026Q4_K_M83 GBdoes not fit
Mistral Small 4 119B-A6.5B Mar 2026Q4_K_M79 GBdoes not fit
Mistral Small 3.2 24B Jun 2025Q3_K_M15 GBfits16K~40~140
Qwen
Qwen3.8 Flash-Next 125B-A6B Aug 2026Q4_K_M78 GBdoes not fit
Qwen3.8 27B Aug 2026 (your pick)Q3_K_M15 GBfits18K~36~120
Qwen3.6 27B Apr 2026Q3_K_M15 GBfits18K~36~120
Qwen3.6 35B-A3B Apr 2026IQ2_M14 GBfits123K~470~1,100
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~43~100

Specifications

Memory
16 GB HBM2
Memory bandwidth
732 GB/s
Bus width
4096-bit
Shader cores
3,584
Tensor cores
0
FP32
9.3 TFLOPS
FP16 (dense)
19 TFLOPS
Power
250 W
Form factor
Dual slot, passive, needs a fan
Interface
PCIe 3.0 x16
Architecture
Pascal
Launched
2016

Source: manufacturer specifications.