Radeon RX 7700 XT
AMD
12GB VRAM · 432 GB/s bandwidth · 70.3 FP16 TFLOPS · 245W TDP
The Radeon RX 7700 XT has 12GB of VRAM with 432 GB/s memory bandwidth and 70.3 TFLOPS FP16 compute. At Q4 quantization, it can comfortably run Gemma 3 4B (108 tok/s), Qwen 2.5 7B (56 tok/s), Llama 3.1 8B (53 tok/s). Models larger than ~20B parameters won't fit even at Q4. Electricity cost is approximately $26/month at 245W TDP.
What LLMs can you run?
| Model | Params | Q4 Weight | Fit | Decode |
|---|---|---|---|---|
| Gemma 3 4B | 4.0B | 2 GB | comfortable | 108 tok/s |
| Qwen 2.5 7B | 7.6B | 4 GB | comfortable | 56 tok/s |
| Llama 3.1 8B | 8.0B | 4 GB | comfortable | 53 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 6750 GRE 12 GB | 12GB | 432 GB/s | 26.4 | 250W |
| Radeon RX 6750 XT | 12GB | 432 GB/s | 26.6 | 250W |
| Radeon RX 9070 GRE | 12GB | 432 GB/s | 68.6 | 220W |
| Arc B580 | 12GB | 456 GB/s | 27.3 | 190W |
| GeForce RTX 4070 GDDR6 | 12GB | 480 GB/s | 29.1 | 200W |
Compare with another GPU
Select another GPU to compare specs and model performance side by side.