GeForce RTX 5090 D V2
NVIDIA
24GB VRAM · 1340 GB/s bandwidth · 104.8 FP16 TFLOPS · 575W TDP
The GeForce RTX 5090 D V2 has 24GB of VRAM with 1340 GB/s memory bandwidth and 104.8 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (368 tok/s), Qwen 2.5 7B (193 tok/s), Llama 3.1 8B (183 tok/s). Models larger than ~41B parameters won't fit even at Q4. Electricity cost is approximately $62/month at 575W TDP.
What LLMs can you run?
| Model | Params | Q4 Weight | Fit | Decode |
|---|---|---|---|---|
| Gemma 3 4B | 4.0B | 2 GB | comfortable | 368 tok/s |
| Qwen 2.5 7B | 7.6B | 4 GB | comfortable | 193 tok/s |
| Llama 3.1 8B | 8.0B | 4 GB | comfortable | 183 tok/s |
| Mistral Small 24B | 24.0B | 12 GB | comfortable | 61 tok/s |
| Gemma 3 27B | 27.4B | 14 GB | comfortable | 53 tok/s |
| Qwen 2.5 Coder 32B | 32.5B | 16 GB | comfortable | 45 tok/s |
| Llama 3.3 70B | 70.6B | 35 GB | won't fit | |
| Qwen 2.5 72B | 72.7B | 36 GB | won't fit | |
| Llama 3.1 405B | 405B | 202 GB | won't fit | |
| DeepSeek R1 671B | 671B | 336 GB | won't fit |
Similar GPUs
| GPU | VRAM | BW | TFLOPS | TDP |
|---|---|---|---|---|
| A30X | 24GB | 1220 GB/s | 10.3 | 230W |
| GeForce RTX 3090 Ti | 24GB | 1010 GB/s | 40.0 | 450W |
| GeForce RTX 4090 | 24GB | 1010 GB/s | 82.6 | 450W |
| GeForce RTX 4090 D | 24GB | 1010 GB/s | 73.5 | 425W |
| Radeon RX 7900 XTX | 24GB | 960 GB/s | 122.8 | 355W |
Compare with another GPU
Select another GPU to compare specs and model performance side by side.