Excellent mid-high range card. 16 GB VRAM runs all 13–14B models comfortably. 132 t/s on 8B models. Great value vs 5090 for most users.
| VRAM | 16 GB |
| Memory Bandwidth | 960 GB/s |
| TDP | 360 W |
| Architecture | Blackwell GB203 |
| Release Year | 2025 |
| MSRP at Launch | $999 |
| Inference Speed (Llama 3.1 8B Q4_K_M) | ~132 tokens/sec |
All models below run comfortably in 16 GB VRAM with Q4_K_M quantization.
| Llama 3.1 Family | 6 GB VRAM · Q4_K_M · ollama run llama3.1 |
| Llama 3.2 Family | 8 GB VRAM · Q4_K_M · ollama run llama3.2-vision:11b |
| Qwen 3 | 10 GB VRAM · Q4_K_M · ollama run qwen3:14b |
| Qwen 3.5 | 6 GB VRAM · Q4_K_M · ollama run qwen3.5:9b |
| Gemma 3 | 8 GB VRAM · Q4_K_M · ollama run gemma3:12b |
| Gemma 4 | 8 GB VRAM · Q4_K_M · ollama run gemma4:12b |
| IBM Granite 4.1 | 6 GB VRAM · Q4_K_M · ollama run granite4.1:8b |
| Phi-4 Family | 9 GB VRAM · Q4_K_M · ollama run phi4 |
Install Ollama then run the recommended model for this GPU:
ollama run qwen3:14b
Yes — the NVIDIA GeForce RTX 5080 has 16 GB VRAM and runs Excellent mid-high range card. 16 GB VRAM runs all 13–14B models comfortably. 132 t/s on 8B models. Great value vs 5090
The NVIDIA GeForce RTX 5080 runs Llama 3.1 8B at ~132 tokens/sec with Q4_K_M quantization.
With 16 GB you can run: Llama 3.1 Family, Llama 3.2 Family, Qwen 3, Qwen 3.5, Gemma 3. Use Ollama for the easiest setup: ollama run qwen3:14b.
← All GPU Reviews | Check Your Hardware | Full Benchmarks | Can I Run It?