NVIDIA A10 24GB
NVIDIA · Ampere · 24GB GDDR6 · PCIe · PCIe 4.0
Current asking prices
Median asking price
$4,288
Observed range
$2,099–$5,236
47 listings· 27 sellers· Updated Aug 25, 2026
Market signals
Derived from observed listings across all SKUs in this class.
▶What do OEM / Original / Compatible mean?
OEMCertified by a server vendor (Dell, HPE, Lenovo). May carry firmware locks and qualifications. Priced higher for vendor support and warranty alignment.
OriginalThe underlying component manufacturer's part, without OEM server-vendor branding or firmware lock. Typically the market pricing reference — platform compatibility should still be verified.
CompatibleThird-party alternatives meeting the same spec. Often 15–40% cheaper. May trigger vendor warnings on OEM-locked platforms — verify before substituting.
OEM Premium
-51%
OEM is currently priced 51% below original — unusual, worth investigating.
Market Spread
86%
Wide spread. Market is fragmented or condition differences are significant.
Liquidity
High
47 samples. High confidence. This market has strong observed data.
▶What do the signal colors mean?
Favorable — Tight spread, meaningful discount, or strong liquidity.
Neutral — Normal market conditions. No action flag.
Investigate — Wide spread, inverted pricing, or low sample count.
High alert — Very wide spread or significant price anomaly.
Insufficient — Too few samples to produce a reliable signal.
Part numbers in this market
5 part numbers tracked. Exact platform, firmware, power, cooling, and OEM compatibility should be verified before purchase.
| Manufacturer | MPN | Certification |
|---|---|---|
| NVIDIA | 490-BHBJ | oem |
| NVIDIA | A10-24GB | original |
| NVIDIA | 900-2G133-0010-000 | original |
| NVIDIA | R6B54A | oem |
| NVIDIA | 4X67A71309 | oem |
Technical specifications
NVIDIA A10 PCIe datacenter GPU with 24GB GDDR6; ai inference workloads
Manufacturer
NVIDIA
Model family
A10
Architecture
Ampere
Form factor
PCIe
Memory
24GB
Memory type
GDDR6
Memory bandwidth
0.6 TB/s
TDP
150W
Interconnect
PCIe
PCIe generation
4
FP16 tensor
125 TFLOPS
Workload class
ai_inference
Launch year
2021
Signals are observations from available data at a point in time — not advice. Verify independently before transacting. Disclaimer