VRAMGlass contains affiliate links. As an eBay Partner, we may be compensated if you make a purchase. As an Amazon Associate I earn from qualifying purchases.We may earn from eBay and Amazon links.Learn more

GPUs tracked64Price history78 daysPrice points (24h)32,149 pointsBiggest 24h dropGeForce RTX 4080-14.4%Biggest 24h riseRadeon RX 7900 XTX+8.2%Updated
$ USD

GeForce RTX 5090 D V2 Price, 24GB VRAM & Local LLMs

Released in China in August 2025, the RTX 5090 D V2 drops to 24GB VRAM but still runs Qwen3.8 27B at 4-bit at about 57 tokens/s, faster than a 4090. Listings often leave out the V2, so go by the 24GB of VRAM.

24h7d30d
Amazon.jp

GeForce RTX 5090 D V2 price history

CurrentNo quotes yet
Amazon.jp
Price updated —
24h7d30d

Not enough data to show a trend

The median price trend will appear once enough valid quotes are available.

Some buy links are affiliate links: we may earn a commission if you buy through them, at no extra cost to you.

GeForce RTX 5090 D V2 VRAM & full specs

  • Memory24 GB · GDDR7
  • Bandwidth1,344 GB/s
  • FP16 / BF16296.9 TFLOPS
  • FP8 / INT8593.8 / 593.8 TOPS
Bus width
384-bit
Architecture
Blackwell (GB202-240)
Cores
21,760
Tensor cores
680
Ecosystem
CUDA
Interface
PCIe 5.0 x16
NVLink
Not supported
Power
575 W
Power connector
16-pin 12V-2x6
Type
Consumer
Launch date
Aug 12, 2025
MSRP
$2,465

What LLMs can a single GeForce RTX 5090 D V2 run?

A single 5090 D V2 reaches 35B-class at 4-bit, with 30B-class MoE at about 150 tokens/s. Context is tight: Gemma 4 31B gets only about 60K.

ModelSizeRuns?Speed t/sMax context
Gemma 4 E4B8B5 GBRuns158128K
Qwen3.5 9B9.7B5.7 GBRuns141.6256K
Gemma 4 12B12B7.1 GBRuns117.4256K
Gemma 4 26B A4B25.2B (3.8B active)16.9 GBRuns136256K
Qwen3.6 27B27.8B16.8 GBRuns55.7117K
Qwen3.8 27B27.8B16.5 GBRuns56.6122K
GLM 4.7 Flash30B (3B active)18.3 GBRuns149.5115K
Gemma 4 31B30.7B18.3 GBRuns50.366K
Qwen3.6 35B A3B36B (3B active)22.1 GBRuns152.2123K

RunsFits fully in VRAM; speed is estimated from VRAM bandwidth.

Needs RAM offloadMoE only: expert weights sit in system RAM, so speed is estimated from 70 GB/s RAM bandwidth.

Too bigWon’t fit on one card at this quantization, even with RAM offload.

Full calculation rules are on the Methodology page.

What can the GeForce RTX 5090 D V2 run with Strata?

With Strata, GeForce RTX 5090 D V2 can run large models that far exceed its VRAM capacity—the bulk of the model stays in RAM and SSD, while the GPU holds only the most frequently used experts. Benchmarks come from the Strata author and community, with pricing filled in by VRAMGlass at current market rates.

Some buy links are affiliate links: we may earn a commission if you buy through them, at no extra cost to you.

Who it suits

Good fit

  1. You want 24GB but faster than a 4090

    The same 27B to 31B dense model runs more than 30% faster, with Qwen3.8 27B at about 57 tokens/s

  2. MoE models fit entirely on the card too

    Qwen3.6 35B A3B and GLM 4.7 Flash at 4-bit both run at around 150 tokens/s without touching system RAM

  3. You want a new card that runs 27B-class models at 4-bit

    24GB is just enough, and Qwen3.8 27B can run up to 122K of context

Not a good fit

  1. Running 27B models at 8-bit

    That takes 29 GB, more than 24GB, so this tier calls for the original 32GB 5090 D

  2. Long prompts and batch work

    Its compute is about 10% lower than even the 4090's

  3. Power draw matters to you

    It takes 575W to get 24GB, while the 4090 draws 450W and the 3090 350W

Before you buy

  1. Make sure it's the V2

    Both versions are called RTX 5090 D: the V2 has 24GB, the original 32GB. Listing titles often leave out “V2”, so check the VRAM capacity in GPU-Z or nvidia-smi; if it shows 24GB, it is this version.

  2. No reference dimensions

    NVIDIA's China website lists the V2's length and slot width as “varies by manufacturer”, so check the specific model before you build. Before launch, Benchlife reported that manufacturers can raise the power limit of factory-overclocked versions to 600W.

  3. Power supply and connector

    As with the 5090, the official recommendation is a 1000W power supply. The connector is 12V-2x6, and with the adapter all four 8-pin plugs must be connected. This connector has melted on the 5090; for the causes and how to prevent it, see the RTX 5090 page.

  4. Check before going multi-GPU

    When the original 5090 D launched, there were claims that its driver restricts multi-GPU and AI workloads, which NVIDIA did not confirm. We haven't found reliable tests showing whether the V2 behaves the same way, so confirm before buying several.

Compared with similar GPUs

GeForce RTX 5090 D V2 vs GeForce RTX 4090, GeForce RTX 5090 D, and GeForce RTX 3090: price, VRAM, bandwidth, compute and local LLM speed compared.

SpecGeForce RTX 5090 D V2GeForce RTX 4090GeForce RTX 5090 DGeForce RTX 3090
Memory
24 GB
24 GBSame
32 GB33% more
24 GBSame
Bandwidth
1,344 GB/s
1,008 GB/s25% lower
1,792 GB/s33% higher
936 GB/s30% lower
BF16 / FP16 compute
297 TFLOPS
330 TFLOPS11% higher
297 TFLOPSSame
142 TFLOPS52% lower
INT8 compute
594 TOPS
661 TOPS11% higher
594 TOPSSame
285 TOPS52% lower
Qwen3.8 27B speed (2-bit)
89.5 t/s
69.3 t/s23% slower
114.6 t/s28% faster
64.8 t/s28% slower
Largest dense model (4-bit)
37B
37BSame
51B38% more
37BSame
Power
575 W
450 W22% lower
575 WSame
350 W39% lower
GPU interconnect
Not supported
Not supported
Not supported
NVLink 112.5 GB/s
Interface
PCIe 5.0 x16
PCIe 4.0 x16
PCIe 5.0 x16
PCIe 4.0 x16
Released
2025-08
2022-10
2025-01
2020-09
Amazon.jp median

Some buy links are affiliate links: we may earn a commission if you buy through them, at no extra cost to you.

Other markets

eBay · United States
N/A
No listings
View
Xianyu · Mainland China
$3,885
5 listings
View

As an eBay Partner, VRAMGlass may be compensated if you buy through the eBay links on this page. The price you pay stays the same.