作者： Jakub Rusinowski · 最后更新： 2026年7月12日
AI性能依然出色。24 GB VRAM与RTX 4090模型兼容性持平。二手价400–600美元。略慢但性价比极高。
| VRAM | 24 GB |
| Memory Bandwidth | 936 GB/s |
| TDP | 350 W |
| Architecture | Ampere GA102 |
| Release Year | 2020 |
| MSRP at Launch | $1,499 |
| Inference Speed (Llama 3.1 8B Q4_K_M) | 60–115 tok/s (estimated) |
| Inference Speed (Llama 3.3 70B Q4_K_M) | Does not fit — needs ~44 GB of 24 GB usable |
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 24 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 32B · 20 GB VRAM · Q4_K_M · ollama run deepseek-r1:32b |
| Qwen 3 | Qwen 3 32B · 21 GB VRAM · Q4_K_M · ollama run qwen3:32b |
| 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 deepseek-r1:32b
Yes — the NVIDIA GeForce RTX 3090 has 24 GB VRAM and runs AI性能依然出色。24 GB VRAM与RTX 4090模型兼容性持平。二手价400–600美元。略慢但性价比极高。
The NVIDIA GeForce RTX 3090 is estimated to run Llama 3.1 8B at 60–115 tok/s with Q4_K_M quantization. Llama 3.3 70B does not fit: it needs about 44 GB against 24 GB usable. These are modelled estimates, not measurements — see /en/methodology.
With 24 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 deepseek-r1:32b.
← All GPU Reviews | Check Your Hardware | Full Benchmarks | Can I Run It?