Radeon PRO V710
AMD
28GB VRAM · 504 GB/s bandwidth · 55.3 FP16 TFLOPS · 158W TDP
The Radeon PRO V710 has 28GB of VRAM with 504 GB/s memory bandwidth and 55.3 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (126 tok/s), Qwen 2.5 7B (66 tok/s), Llama 3.1 8B (62 tok/s). Models larger than ~48B parameters won't fit even at Q4. Electricity cost is approximately $17/month at 158W TDP.
What LLMs can you run?
| Model | Params | Q4 Weight | Fit | Decode |
|---|---|---|---|---|
| Gemma 3 4B | 4.0B | 2 GB | comfortable | 126 tok/s |
| Qwen 2.5 7B | 7.6B | 4 GB | comfortable | 66 tok/s |
| Llama 3.1 8B | 8.0B | 4 GB | comfortable | 62 tok/s |
| Mistral Small 24B | 24.0B | 12 GB | tight | 21 tok/s |
| Gemma 3 27B | 27.4B | 14 GB | tight | 18 tok/s |
| Qwen 2.5 Coder 32B | 32.5B | 16 GB | tight | 15 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 |
|---|---|---|---|---|
| Radeon PRO V620 | 32GB | 512 GB/s | 40.5 | 300W |
| Radeon PRO W6800 | 32GB | 512 GB/s | 35.7 | 250W |
| Arc Pro B60 | 24GB | 456 GB/s | 24.6 | 200W |
| Quadro P6000 | 24GB | 432 GB/s | 0.2 | 250W |
| Radeon AI PRO 9600D | 32GB | 576 GB/s | 49.6 | 150W |
Compare with another GPU
Select another GPU to compare specs and model performance side by side.