AMD's answer to the RTX 4090. 24 GB VRAM at a lower price. ROCm support is improving. Works great with Ollama on Linux. Slightly slower than RTX 4090 due to ROCm overhead.
| VRAM | 24 GB |
| Memory Bandwidth | 960 GB/s |
| TDP | 355 W |
| Architecture | RDNA 3 Navi 31 |
| Release Year | 2022 |
| MSRP at Launch | $999 |
| Inference Speed (Llama 3.1 8B Q4_K_M) | ~85 tokens/sec |
| Inference Speed (Llama 3.3 70B Q4_K_M) | ~20 tokens/sec |
All models below run comfortably in 24 GB VRAM with Q4_K_M quantization.
| Llama 3.3 | 43 GB VRAM (smallest variant — needs more VRAM or a lower quant) · Q2_K_XS (Tight) · ollama run llama3.3 |
| Llama 3.1 Family | 6 GB VRAM · Q4_K_M · ollama run llama3.1 |
| DeepSeek R1 | 20 GB VRAM · Q4_K_M · ollama run deepseek-r1:32b |
| Qwen 3 | 20 GB VRAM · Q4_K_M · ollama run qwen3:32b |
| Gemma 3 | 17 GB VRAM · Q4_K_M · ollama run gemma3:27b |
| Mistral Small 3.1 | 14 GB VRAM · Q4_K_M · ollama run mistral-small3.1 |
| Phi-4 Family | 9 GB VRAM · Q4_K_M · ollama run phi4 |
Install Ollama then run the recommended model for this GPU:
ollama run deepseek-r1:32b
Yes — the AMD Radeon RX 7900 XTX has 24 GB VRAM and runs AMD's answer to the RTX 4090. 24 GB VRAM at a lower price. ROCm support is improving. Works great with Ollama on Linux.
The AMD Radeon RX 7900 XTX runs Llama 3.1 8B at ~85 tokens/sec with Q4_K_M quantization. For the 70B model it achieves ~20 tokens/sec.
With 24 GB you can run: Llama 3.3, Llama 3.1 Family, DeepSeek R1, Qwen 3, Gemma 3. Use Ollama for the easiest setup: ollama run deepseek-r1:32b.
← All GPU Reviews | Check Your Hardware | Full Benchmarks | Can I Run It?