NVIDIA GeForce RTX 4060 Ti 16GB vs NVIDIA GeForce RTX 5090
For running models locally, priced in Germany. At 128k context the first runs 5 models fully in memory, the second 24.
Specifications
| Spec | NVIDIA GeForce RTX 4060 Ti 16GB | NVIDIA GeForce RTX 5090 |
|---|---|---|
| GPU | GeForce RTX 4060 Ti 16GB | GeForce RTX 5090 |
| Memory | 16 GB GDDR6 | 32 GB GDDR7 |
| Memory bus | 128-bit | 512-bit |
| Memory bandwidth | 288 GB/s | 1,792 GB/s |
| FP16 compute | 44 TFLOPS | 209 TFLOPS |
| Software | CUDA | CUDA |
| Board power | 165 W | 575 W |
| PCIe generation | Gen 4 | Gen 5 |
| PCIe lanes | x8 | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | NVIDIA GeForce RTX 4060 Ti 16GB | NVIDIA GeForce RTX 5090 |
|---|---|---|
| Qwen 3.8 27B | offload | 36tok/sUD-Q6_K |
| Qwen 3.6 27B | offload | 36tok/sQ6_K |
| Gemma 4 31B | offload | 37tok/sQ4_K_M |
| Qwen 3.6 35B-A3B | offload | 128tok/sUD-Q6_K |
| Qwen 3.5 27B | offload | 36tok/sQ6_K |
| Gemma 4 26B-A4B | offload | 95tok/sQ8_0 |
| Qwen 3.5 35B-A3B | offload | 129tok/sQ6_K |
| GLM 4.7 Flash | offload | 60tok/sQ6_K |
| gpt-oss 20B | offload | 118tok/sMXFP4 |
| Kimi Linear 48B-A3B | offload | 227tok/sQ4_K_M |
| Qwen3 Coder 30B-A3B | offload | 45tok/sQ4_K_M |
| Gemma 4 12B | 15tok/sQ6_K | 73tok/sQ8_0 |
| Qwen 3.5 9B | 13tok/sQ8_0 | 80tok/sQ8_0 |
| Gemma 3 27B | offload | 37tok/sQ5_K_M |
| Ministral 3 14B | offload | 36tok/sQ5_K_M |
| Qwen3 14B | offload | 35tok/sQ5_K_M |
| DeepSeek R1 0528 Qwen3 8B | offload | 40tok/sQ8_0 |
| Qwen3 8B | offload | 40tok/sQ8_0 |
| Qwen 3.5 4B | 20tok/sQ8_0 | 126tok/sQ8_0 |
| Ministral 3 8B | offload | 41tok/sQ8_0 |
| Granite 4.2 8B | offload | 36tok/sQ8_0 |
| Gemma 4 E4B | 15tok/sQ8_0 | 93tok/sQ8_0 |
| LFM2.5 8B-A1B | 15tok/sUD-Q6_K | 89tok/sQ8_0 |
| Llama 3.1 8B | offload | 47tok/sQ6_K |
| Qwen 3.5 122B-A10B | won't run | offload |
| Nemotron 3 Super 120B-A12B | won't run | offload |
| Qwen3 Coder Next | won't run | offload |
| Mistral Small 4 119B | won't run | offload |
| Devstral Small 2 24B | offload | offload |
| Qwen3 Next 80B-A3B | won't run | offload |
| Nemotron 3.5 Lightning 30B-A3B | offload | offload |
| Qwen3 32B | won't run | offload |
| Mistral Small 3.2 24B | offload | offload |
| DeepSeek R1 Distill Qwen 32B | won't run | offload |
| Phi-4 14B | 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 |
| 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 |