GeForce RTX 5090 D V2 Price & Used Prices: Which Local LLMs Can It Run?
Price alert
We'll email you when the eBay (US) price reaches your target.
The RTX 5090 D V2 is NVIDIA's 24GB China-market card from August 2025, running Qwen3.8 27B at 4-bit at about 57 tokens/s. Listings often omit V2.
eBay
GeForce RTX 5090 D V2 price history
eBay
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.
Full GeForce RTX 5090 D V2 specifications
- 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
- $2,466
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.
| Model | Size | Runs? | Speed t/s | Max context |
|---|---|---|---|---|
 Gemma 4 E4B8B | 3.8 GB | Runs | 193.7 | 128K |
 Qwen3.5 9B9.7B | 4.1 GB | Runs | 181.6 | 256K |
| Gemma 4 12B12B | 4.7 GB | Runs | 161.7 | 256K |
| Gemma 4 26B A4B25.2B (3.8B active) | 10.5 GB | Runs | 155.9 | 256K |
| Qwen3.6 27B27.8B | 11.8 GB | Runs | 76.3 | 192K |
| Qwen3.8 27B27.8B | 9.8 GB | Runs | 89.5 | 221K |
 GLM 4.7 Flash30B (3B active) | 11.9 GB | Runs | 164.9 | 198K |
| Gemma 4 31B30.7B | 11.8 GB | Runs | 73.7 | 143K |
| Qwen3.6 35B A3B36B (3B active) | 12.3 GB | Runs | 173.1 | 256K |
| Model | Size | Runs? | Speed t/s | Max context |
|---|---|---|---|---|
| Gemma 4 E4B8B | 5 GB | Runs | 158 | 128K |
| Qwen3.5 9B9.7B | 5.7 GB | Runs | 141.6 | 256K |
| Gemma 4 12B12B | 7.1 GB | Runs | 117.4 | 256K |
| Gemma 4 26B A4B25.2B (3.8B active) | 16.9 GB | Runs | 136 | 256K |
| Qwen3.6 27B27.8B | 16.8 GB | Runs | 55.7 | 117K |
| Qwen3.8 27B27.8B | 16.5 GB | Runs | 56.6 | 122K |
| GLM 4.7 Flash30B (3B active) | 18.3 GB | Runs | 149.5 | 115K |
| Gemma 4 31B30.7B | 18.3 GB | Runs | 50.3 | 66K |
| Qwen3.6 35B A3B36B (3B active) | 22.1 GB | Runs | 152.2 | 123K |
| Model | Size | Runs? | Speed t/s | Max context |
|---|---|---|---|---|
| Gemma 4 E4B8B | 8.2 GB | Runs | 106 | 128K |
| Qwen3.5 9B9.7B | 9.5 GB | Runs | 93 | 256K |
| Gemma 4 12B12B | 12.7 GB | Runs | 71.7 | 256K |
| Gemma 4 26B A4B25.2B (3.8B active) | 26.9 GB | Needs RAM offload | 27.1 | 256K |
| Qwen3.6 27B27.8B | 28.6 GB | Too big | — | — |
| Qwen3.8 27B27.8B | 29 GB | Too big | — | — |
| GLM 4.7 Flash30B (3B active) | 31.8 GB | Needs RAM offload | 23.1 | 198K |
| Gemma 4 31B30.7B | 32.6 GB | Too big | — | — |
| Qwen3.6 35B A3B36B (3B active) | 36.9 GB | Needs RAM offload | 35.8 | 256K |
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.
Who it suits
Good fit
- 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
- 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
- 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
- Running 27B models at 8-bit
That takes 29 GB, more than 24GB, so this tier calls for the original 32GB 5090 D
- Long prompts and batch work
Its compute is about 10% lower than even the 4090's
- Power draw matters to you
It takes 575W to get 24GB, while the 4090 draws 450W and the 3090 350W
Before you buy
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.
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.
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.
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.
| Spec | GeForce RTX 5090 D V2 | GeForce RTX 4090 | GeForce RTX 5090 D | GeForce 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 |
| eBay median |
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.
Amazon.jp
Xianyu