TITAN V
NVIDIA
12GB VRAM · 651 GB/s bandwidth · 29.8 FP16 TFLOPS · 250W TDP
The TITAN V has 12GB of VRAM with 651 GB/s memory bandwidth and 29.8 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (179 tok/s), Qwen 2.5 7B (94 tok/s), Llama 3.1 8B (89 tok/s). Models larger than ~20B parameters won't fit even at Q4. Electricity cost is approximately $27/month at 250W TDP.
What LLMs can you run?
| Model | Params | Q4 Weight | Fit | Decode |
|---|---|---|---|---|
| Gemma 3 4B | 4.0B | 2 GB | comfortable | 179 tok/s |
| Qwen 2.5 7B | 7.6B | 4 GB | comfortable | 94 tok/s |
| Llama 3.1 8B | 8.0B | 4 GB | comfortable | 89 tok/s |
| Mistral Small 24B | 24.0B | 12 GB | won't fit | |
| Gemma 3 27B | 27.4B | 14 GB | won't fit | |
| Qwen 2.5 Coder 32B | 32.5B | 16 GB | won't fit | |
| 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 |
|---|---|---|---|---|
| GeForce RTX 5070 | 12GB | 672 GB/s | 30.9 | 250W |
| Tesla P100 PCIe 12 GB | 12GB | 549 GB/s | 19.1 | 250W |
| TITAN Xp | 12GB | 547 GB/s | 0.2 | 250W |
| RTX A5000-12Q | 12GB | 768 GB/s | 27.8 | 230W |
| GeForce RTX 4070 | 12GB | 504 GB/s | 29.1 | 200W |
Compare with another GPU
Select another GPU to compare specs and model performance side by side.