Radeon PRO W7500
AMD
8GB VRAM · 256 GB/s bandwidth · 24.4 FP16 TFLOPS · 70W TDP
The Radeon PRO W7500 has 8GB of VRAM with 256 GB/s memory bandwidth and 24.4 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (64 tok/s), Qwen 2.5 7B (33 tok/s), Llama 3.1 8B (31 tok/s). Models larger than ~14B parameters won't fit even at Q4. Electricity cost is approximately $8/month at 70W TDP.
What LLMs can you run?
| Model | Params | Q4 Weight | Fit | Decode |
|---|---|---|---|---|
| Gemma 3 4B | 4.0B | 2 GB | comfortable | 64 tok/s |
| Qwen 2.5 7B | 7.6B | 4 GB | comfortable | 33 tok/s |
| Llama 3.1 8B | 8.0B | 4 GB | comfortable | 31 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 |
|---|---|---|---|---|
| Radeon RX 6600 XT | 8GB | 256 GB/s | 21.2 | 160W |
| GeForce GTX 1070 | 8GB | 256 GB/s | 0.1 | 150W |
| GeForce GTX 1070 GDDR5X | 8GB | 256 GB/s | 0.1 | 150W |
| GeForce GTX 1070 Ti | 8GB | 256 GB/s | 0.1 | 180W |
| Quadro P4000 | 8GB | 243 GB/s | 0.1 | 105W |
Compare with another GPU
Select another GPU to compare specs and model performance side by side.