AMD Radeon RX 9060 XT 8GB
AMD · 8GB GDDR6 · Can run 35 models
Buy Amazon
| Manufacturer | AMD |
| VRAM | 8 GB |
| Memory Type | GDDR6 |
| Architecture | RDNA 4 |
| Stream Procs | 2,048 |
| Bandwidth | 269 GB/s |
| TDP | 150W |
| MSRP | $279 |
| Released | Jun 5, 2025 |
AI Notes
The RX 9060 XT 8GB is a budget-friendly RDNA 4 card with enough VRAM to handle 7B models comfortably at Q4 quantization. The halved memory bandwidth compared to the 16GB variant limits throughput on larger workloads. ROCm support continues to improve for RDNA 4, but NVIDIA remains easier to set up for AI inference.
Compatible Models
| Model | Parameters | Best Quant | VRAM Used | Fit | Est. Speed |
|---|---|---|---|---|---|
| Qwen 3 0.6B | 600M | Q4_K_M | 2.5 GB | Runs | ~108 tok/s |
| Gemma 3 1B | 1B | Q8_0 | 2 GB | Runs | ~135 tok/s |
| Llama 3.2 1B | 1B | Q8_0 | 3 GB | Runs | ~90 tok/s |
| DeepSeek R1 1.5B | 1.5B | Q8_0 | 3 GB | Runs | ~90 tok/s |
| Gemma 2 2B | 2B | Q8_0 | 4 GB | Runs | ~67 tok/s |
| Gemma 3n E2B | 2B | Q4_K_M | 3.3 GB | Runs | ~82 tok/s |
| Llama 3.2 3B | 3B | Q8_0 | 5 GB | Runs | ~54 tok/s |
| Phi-3 Mini 3.8B | 3.8B | Q8_0 | 5.8 GB | Runs | ~46 tok/s |
| Phi-4 Mini 3.8B | 3.8B | Q4_K_M | 4.5 GB | Runs | ~60 tok/s |
| Gemma 3 4B | 4B | Q4_K_M | 5 GB | Runs | ~54 tok/s |
| Gemma 3n E4B | 4B | Q4_K_M | 4.5 GB | Runs | ~60 tok/s |
| Qwen 3 4B | 4B | Q4_K_M | 4.5 GB | Runs | ~60 tok/s |
| Falcon 3 7B | 7B | Q4_K_M | 6.8 GB | Runs | ~40 tok/s |
| Qwen 2.5 VL 7B | 7B | Q4_K_M | 7 GB | Runs (tight) | ~38 tok/s |
| Cogito 8B | 8B | Q4_K_M | 7.5 GB | Runs (tight) | ~36 tok/s |
| DeepSeek R1 8B | 8B | Q4_K_M | 7.5 GB | Runs (tight) | ~36 tok/s |
| Nemotron 3 Nano 8B | 8B | Q4_K_M | 7.5 GB | Runs (tight) | ~36 tok/s |
| Qwen 3 8B | 8B | Q4_K_M | 7.5 GB | Runs (tight) | ~36 tok/s |
| DeepSeek R1 7B | 7B | Q8_0 | 9 GB | CPU Offload | ~9 tok/s |
| Mistral 7B | 7B | Q8_0 | 9 GB | CPU Offload | ~9 tok/s |
| Qwen 2.5 7B | 7B | Q8_0 | 9 GB | CPU Offload | ~9 tok/s |
| Qwen 2.5 Coder 7B | 7B | Q8_0 | 9 GB | CPU Offload | ~9 tok/s |
| Llama 3.1 8B | 8B | Q8_0 | 10 GB | CPU Offload | ~8 tok/s |
| Gemma 2 9B | 9B | Q8_0 | 11 GB | CPU Offload | ~7 tok/s |
| Falcon 3 10B | 10B | Q4_K_M | 8.5 GB | CPU Offload | ~10 tok/s |
| Llama 3.2 Vision 11B | 11B | Q4_K_M | 8.5 GB | CPU Offload | ~10 tok/s |
| Gemma 3 12B | 12B | Q4_K_M | 10.5 GB | CPU Offload | ~8 tok/s |
| Mistral Nemo 12B | 12B | Q4_K_M | 9.5 GB | CPU Offload | ~8 tok/s |
| DeepSeek R1 14B | 14B | Q4_K_M | 9.9 GB | CPU Offload | ~8 tok/s |
| Phi-4 14B | 14B | Q4_K_M | 9.9 GB | CPU Offload | ~8 tok/s |
| Phi-4 Reasoning 14B | 14B | Q4_K_M | 11 GB | CPU Offload | ~7 tok/s |
| Qwen 2.5 14B | 14B | Q4_K_M | 9.9 GB | CPU Offload | ~8 tok/s |
| Qwen 2.5 Coder 14B | 14B | Q4_K_M | 12 GB | CPU Offload | ~7 tok/s |
| Qwen 3 14B | 14B | Q4_K_M | 12 GB | CPU Offload | ~7 tok/s |
| StarCoder2 15B | 15B | Q4_K_M | 10.5 GB | CPU Offload | ~8 tok/s |
34
model(s) are too large for this hardware.