NVIDIA GeForce RTX 3090 Ti vs NVIDIA RTX PRO 6000 Blackwell
In short
The NVIDIA RTX PRO 6000 Blackwell has more memory for models: 96 GB against 24 GB. At 32k context the NVIDIA RTX PRO 6000 Blackwell runs 41 of the models we track fully in memory and the NVIDIA GeForce RTX 3090 Ti 26; only the NVIDIA RTX PRO 6000 Blackwell holds DeepSeek V4 Flash. On the models both run fully in memory, the NVIDIA RTX PRO 6000 Blackwell is about 1.8× as fast as the NVIDIA GeForce RTX 3090 Ti (estimated, median across models). In Germany the NVIDIA GeForce RTX 3090 Ti costs 2.500 € at Amazon and the NVIDIA RTX PRO 6000 Blackwell 19.076 € at eBay: the NVIDIA GeForce RTX 3090 Ti is 16.576 € cheaper.
Updated . Speeds are estimates; how they are worked out.
Specifications
| Spec | NVIDIA GeForce RTX 3090 Ti | NVIDIA RTX PRO 6000 Blackwell |
|---|---|---|
| GPU | GeForce RTX 3090 Ti | RTX PRO 6000 Blackwell |
| Memory | 24 GB GDDR6X | 96 GB GDDR7 |
| Memory bus | 384-bit | 512-bit |
| Memory bandwidth | 1,008 GB/s | 1,792 GB/s |
| FP16 compute | 80 TFLOPS | 504 TFLOPS |
| Software | CUDA | CUDA |
| Board power | 450 W | 600 W |
| PCIe generation | Gen 4 | Gen 5 |
| PCIe lanes | x16 | x16 |
What each runs
Estimated decode speed with the most precise quant that fits each one est.
| Model | NVIDIA GeForce RTX 3090 Ti | NVIDIA RTX PRO 6000 Blackwell |
|---|---|---|
| DeepSeek V4 Flash | won't run | 69tok/sUD-Q2_K_XL |
| Qwen 3.8 Flash Next | won't run | 21tok/sUD-Q3_K_XL |
| Qwen 3.8 27B | 28tok/sUD-Q5_K_M | 35tok/sQ8_0 |
| MiniMax M2.7 | won't run | 56tok/sUD-Q2_K_XL |
| Qwen 3.5 122B-A10B | offload | 81tok/sQ5_K_M |
| Qwen 3.6 27B | 29tok/sQ5_K_M | 36tok/sQ8_0 |
| Gemma 4 31B | 29tok/sQ4_K_M | 31tok/sQ8_0 |
| Qwen3 Coder Next | offload | 133tok/sQ8_0 |
| Nemotron 3 Super 120B-A12B | won't run | 79tok/sUD-Q4_K_M |
| gpt-oss 120B | won't run | 154tok/sMXFP4 |
| Mistral Small 4 119B | offload | 101tok/sUD-Q6_K |
| Qwen 3.6 35B-A3B | 145tok/sUD-Q4_K_M | 175tok/sQ8_0 |
| Qwen 3.5 27B | 29tok/sQ5_K_M | 36tok/sQ8_0 |
| Gemma 4 26B-A4B | 84tok/sUD-Q6_K | 132tok/sQ8_0 |
| GLM 4.5 Air | offload | 35tok/sQ5_K_M |
| Qwen 3.5 35B-A3B | 146tok/sQ4_K_M | 175tok/sQ8_0 |
| GLM 4.7 Flash | 70tok/sQ5_K_M | 95tok/sQ8_0 |
| Devstral Small 2 24B | 28tok/sQ5_K_M | 37tok/sQ8_0 |
| Qwen3 Next 80B-A3B | offload | 166tok/sQ8_0 |
| Nemotron 3.5 Lightning 30B-A3B | offload | 187tok/sUD-Q6_K_XL |
| gpt-oss 20B | 116tok/sMXFP4 | 206tok/sMXFP4 |
| Qwen3 Coder 30B-A3B | 74tok/sQ4_K_M | 104tok/sQ8_0 |
| Kimi Linear 48B-A3B | offload | 191tok/sQ8_0 |
| Qwen3 32B | offload | 26tok/sQ8_0 |
| Gemma 4 12B | 46tok/sQ8_0 | 82tok/sQ8_0 |
| Qwen 3.5 9B | 59tok/sQ8_0 | 104tok/sQ8_0 |
| Mistral Small 3.2 24B | 28tok/sQ5_K_M | 37tok/sQ8_0 |
| Gemma 3 27B | 28tok/sQ5_K_M | 35tok/sQ8_0 |
| DeepSeek R1 Distill Qwen 32B | offload | 26tok/sQ8_0 |
| Llama 3.3 70B | won't run | 13tok/sQ8_0 |
| Ministral 3 14B | 32tok/sQ8_0 | 56tok/sQ8_0 |
| Qwen3 14B | 30tok/sQ8_0 | 53tok/sQ8_0 |
| DeepSeek R1 0528 Qwen3 8B | 46tok/sQ8_0 | 82tok/sQ8_0 |
| Qwen3 8B | 46tok/sQ8_0 | 82tok/sQ8_0 |
| Phi-4 14B | 28tok/sQ8_0 | 50tok/sQ8_0 |
| Qwen 3.5 4B | 112tok/sQ8_0 | 198tok/sQ8_0 |
| Ministral 3 8B | 46tok/sQ8_0 | 82tok/sQ8_0 |
| Granite 4.2 8B | 43tok/sQ8_0 | 76tok/sQ8_0 |
| Gemma 4 E4B | 68tok/sQ8_0 | 121tok/sQ8_0 |
| LFM2.5 8B-A1B | 140tok/sQ8_0 | 249tok/sQ8_0 |
| Llama 3.1 8B | 57tok/sQ6_K | 102tok/sQ6_K |
| GLM 5.3 Flash | won't run | offload |
Questions
- Which is better for local AI, the NVIDIA GeForce RTX 3090 Ti or the NVIDIA RTX PRO 6000 Blackwell?
- Choose the NVIDIA RTX PRO 6000 Blackwell to run bigger models. Choose the NVIDIA RTX PRO 6000 Blackwell for speed. Choose the NVIDIA GeForce RTX 3090 Ti to spend less.
- Which can run bigger models, the NVIDIA GeForce RTX 3090 Ti or the NVIDIA RTX PRO 6000 Blackwell?
- At 32k context the NVIDIA RTX PRO 6000 Blackwell runs 41 of the models we track fully in memory and the NVIDIA GeForce RTX 3090 Ti 26; only the NVIDIA RTX PRO 6000 Blackwell holds DeepSeek V4 Flash.
- Which is faster for local AI, the NVIDIA GeForce RTX 3090 Ti or the NVIDIA RTX PRO 6000 Blackwell?
- On the models both run fully in memory, the NVIDIA RTX PRO 6000 Blackwell is about 1.8× as fast as the NVIDIA GeForce RTX 3090 Ti (estimated, median across models).
- What is the price difference between the NVIDIA GeForce RTX 3090 Ti and the NVIDIA RTX PRO 6000 Blackwell?
- In Germany the NVIDIA GeForce RTX 3090 Ti costs 2.500 € at Amazon and the NVIDIA RTX PRO 6000 Blackwell 19.076 € at eBay: the NVIDIA GeForce RTX 3090 Ti is 16.576 € cheaper.
More comparisons
- Mac Studio M3 Ultra 96GB vs NVIDIA RTX PRO 6000 Blackwell
- AMD Radeon AI PRO R9700 vs NVIDIA GeForce RTX 3090 Ti
- NVIDIA GeForce RTX 3090 vs NVIDIA GeForce RTX 3090 Ti
- NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 4090
- NVIDIA GeForce RTX 3090 Ti vs NVIDIA GeForce RTX 5090
- NVIDIA GeForce RTX 3090 Ti vs AMD Radeon RX 7900 XTX
- NVIDIA GeForce RTX 5090 vs NVIDIA RTX PRO 6000 Blackwell