作者： Jakub Rusinowski · 最后更新： 2026年7月12日
20 GB VRAM是独特的甜蜜点——比16GB显卡能支持更大上下文的14B模型。适合想要比7800 XT更多VRAM的AMD用户。
| VRAM | 20 GB |
| Memory Bandwidth | 800 GB/s |
| TDP | 315 W |
| Architecture | RDNA 3 Navi 31 |
| Release Year | 2022 |
| MSRP at Launch | $899 |
| Inference Speed (Llama 3.1 8B Q4_K_M) | 47–98 tok/s (estimated) |
| Inference Speed (Llama 3.3 70B Q4_K_M) | Does not fit — needs ~44 GB of 20 GB usable |
or compare on Vast.ai from $0.35/hr (typical low · varies)
As an Amazon Associate we earn from qualifying purchases. Cloud GPU links are referral links — we may earn a commission at no extra cost to you.
All models below run comfortably in 20 GB VRAM with Q4_K_M quantization.
| Llama 3.1 Family | Llama 3.1 8B Instruct · 6 GB VRAM · Q4_K_M · ollama run llama3.1 |
| DeepSeek R1 | DeepSeek R1 Distill Qwen 14B · 9 GB VRAM · Q4_K_M · ollama run deepseek-r1:14b |
| Qwen 3 | Qwen 3 30B-A3B (MoE) · 19 GB VRAM · Q4_K_M · ollama run qwen3:30b-a3b |
| Gemma 3 | Gemma 3 27B Instruct · 17 GB VRAM · Q4_K_M · ollama run gemma3:27b |
| Mistral Small 3.1 | Mistral Small 3.1 24B · 15 GB VRAM · Q4_K_M · ollama run mistral-small3.1 |
| Phi-4 Family | Phi-4 (14B) · 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 AMD Radeon RX 7900 XT has 20 GB VRAM and runs 20 GB VRAM是独特的甜蜜点——比16GB显卡能支持更大上下文的14B模型。适合想要比7800 XT更多VRAM的AMD用户。
The AMD Radeon RX 7900 XT is estimated to run Llama 3.1 8B at 47–98 tok/s with Q4_K_M quantization. Llama 3.3 70B does not fit: it needs about 44 GB against 20 GB usable. These are modelled estimates, not measurements — see /en/methodology.
With 20 GB you can run: Llama 3.1 Family, DeepSeek R1, Qwen 3, Gemma 3, Mistral Small 3.1. Use Ollama for the easiest setup: ollama run qwen3:14b.
← All GPU Reviews | Check Your Hardware | Full Benchmarks | Can I Run It?