AMD Radeon RX 9060 XT 16GB vs NVIDIA GeForce RTX 4090
For running models locally, priced in Germany. At 64k context the first runs 10 models fully in memory, the second 22.
Specifications
| Spec | AMD Radeon RX 9060 XT 16GB | NVIDIA GeForce RTX 4090 |
|---|---|---|
| GPU | Radeon RX 9060 XT 16GB | GeForce RTX 4090 |
| Memory | 16 GB GDDR6 | 24 GB GDDR6X |
| Memory bus | 128-bit | 384-bit |
| Memory bandwidth | 320 GB/s | 1,008 GB/s |
| FP16 compute | 103 TFLOPS | 165 TFLOPS |
| Software | ROCm | CUDA |
| Board power | 160 W | 450 W |
| PCIe generation | Gen 5 | Gen 4 |
| PCIe lanes | x16 | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | AMD Radeon RX 9060 XT 16GB | NVIDIA GeForce RTX 4090 |
|---|---|---|
| Qwen 3.8 27B | offload | 30tok/sUD-Q4_K_M |
| Qwen 3.6 27B | offload | 26tok/sQ5_K_M |
| Qwen 3.6 35B-A3B | offload | 115tok/sUD-Q4_K_M |
| Qwen 3.5 27B | offload | 30tok/sQ4_K_M |
| Gemma 4 26B-A4B | offload | 78tok/sUD-Q5_K_M |
| Qwen 3.5 35B-A3B | offload | 116tok/sQ4_K_M |
| GLM 4.7 Flash | offload | 57tok/sQ4_K_M |
| gpt-oss 20B | 26tok/sMXFP4 | 93tok/sMXFP4 |
| Gemma 4 12B | 13tok/sQ8_0 | 44tok/sQ8_0 |
| Qwen 3.5 9B | 15tok/sQ8_0 | 53tok/sQ8_0 |
| Gemma 3 27B | offload | 28tok/sQ4_K_M |
| Ministral 3 14B | offload | 29tok/sQ6_K |
| Qwen3 14B | offload | 27tok/sQ6_K |
| DeepSeek R1 0528 Qwen3 8B | 12tok/sQ4_K_M | 34tok/sQ8_0 |
| Qwen3 8B | 12tok/sQ4_K_M | 34tok/sQ8_0 |
| Phi-4 14B | offload | 26tok/sQ5_K_M |
| Qwen 3.5 4B | 26tok/sQ8_0 | 94tok/sQ8_0 |
| Ministral 3 8B | 12tok/sQ4_K_M | 34tok/sQ8_0 |
| Granite 4.2 8B | offload | 31tok/sQ8_0 |
| Gemma 4 E4B | 17tok/sQ8_0 | 62tok/sQ8_0 |
| LFM2.5 8B-A1B | 25tok/sQ8_0 | 88tok/sQ8_0 |
| Llama 3.1 8B | 12tok/sQ5_K_M | 41tok/sQ6_K |
| Qwen 3.5 122B-A10B | won't run | offload |
| Gemma 4 31B | offload | offload |
| Qwen3 Coder Next | won't run | offload |
| Mistral Small 4 119B | offload | offload |
| Devstral Small 2 24B | offload | offload |
| Qwen3 Next 80B-A3B | won't run | offload |
| Nemotron 3.5 Lightning 30B-A3B | offload | offload |
| Kimi Linear 48B-A3B | offload | offload |
| Qwen3 Coder 30B-A3B | offload | offload |
| Qwen3 32B | offload | offload |
| Mistral Small 3.2 24B | offload | offload |
| DeepSeek R1 Distill Qwen 32B | offload | offload |
| DeepSeek V4 Flash | won't run | won't run |
| GLM 5.3 Flash | won't run | won't run |
| Qwen 3.8 Flash Next | won't run | won't run |
| MiniMax M2.7 | won't run | won't run |
| Nemotron 3 Super 120B-A12B | won't run | won't run |
| gpt-oss 120B | won't run | won't run |
| GLM 4.5 Air | won't run | won't run |
| Llama 3.3 70B | won't run | won't run |