1x RTX 3090 (used) vs 1x RTX PRO 6000 Blackwell
The 1x RTX PRO 6000 Blackwell gives a model 96 GB to work in, against 24 GB on the 1x RTX 3090 (used). The 1x RTX PRO 6000 Blackwell has 1.9× the memory bandwidth (1,792 against 936 GB/s), which sets the ceiling on generation speed. The largest 4-bit model each holds at 8,192 tokens of context: Qwen3.6 35B-A3B on the 1x RTX 3090 (used), Nemotron 3 Super 120B-A12B on the 1x RTX PRO 6000 Blackwell. The 1x RTX 3090 (used) has no complete price: used GPU price not included. Rows where the two differ are tinted.
Single GPU
1x RTX 3090 (used)
The cheapest way to 24 GB of CUDA memory: one used RTX 3090 on a current AM5 desktop. It runs 24-32B dense models at 4-bit and small MoE models entirely on the GPU.
gpt-oss-20b, 4-bit: 162 tok/s
Single GPU
1x RTX PRO 6000 Blackwell
96 GB on one card, so 70B dense at 8-bit or ~120B-class MoE models at 4-bit with no multi-GPU split. The GPU price has nearly doubled since launch.
gpt-oss-20b, 4-bit: 287 tok/s
| Specification | 1x RTX 3090 (used) | 1x RTX PRO 6000 Blackwell |
|---|---|---|
| Kind | Single GPU · DIY | Single GPU · DIY |
| Chip or GPUs | RTX 3090 | RTX PRO 6000 Blackwell Workstation Edition |
| Memory | 24 GB VRAM + 64 GB RAM | 96 GB VRAM + 128 GB RAM |
| Memory for models | 24 GB (VRAM) | 96 GB (VRAM) |
| Memory bandwidth | 936 GB/s | 1,792 GB/s |
| FP16 compute | 71.2 TFLOPS | not published |
| Price | ~$2,944 + unpriced parts (used GPU price not included) | ~$20,833 (sum of parts) |
| Largest at 4-bit, 8k context | Qwen3.6 35B-A3B | Nemotron 3 Super 120B-A12B |
| Software | CUDA, Vulkan | CUDA, Vulkan |
| Power | 1000 W power supply | 1200 W power supply |
What each one runs
Every model in the catalog that at least one of the two holds at 4-bit with 8,192 tokens of context. Copper speeds are measured medians; outlined ones are estimates. Rows where only one fits, or where the speed differs by more than a quarter, are tinted.
| Model | 1x RTX 3090 (used) | 1x RTX PRO 6000 Blackwell |
|---|---|---|
| Nemotron 3 Super 120B-A12B120B, 12B active · 81.0 GB file | does not fit | ~51–75 tok/sestimate |
| Qwen3.5 122B-A10B122B, 10B active · 71.3 GB file | does not fit | 98 tok/smedian of 1 run |
| Mistral Medium 3.5 128B128B · 69.8 GB file | does not fit | ~12–18 tok/sestimate |
| GLM-4.5-Air106B, 12B active · 68.0 GB file | does not fit | 101 tok/smedian of 1 run |
| Mistral Small 4 119B (2603)119B, 6.5B active · 67.6 GB file | does not fit | ~112–164 tok/sestimate |
| Llama 4 Scout 17B-16E Instruct109B, 17B active · 60.9 GB file | does not fit | ~44–64 tok/sestimate |
| gpt-oss-120b117B, 5.1B active · 58.5 GB file | does not fit | 202 tok/smedian of 4 runs |
| Qwen3 Coder Next80B, 3B active · 45.2 GB file | does not fit | 91 tok/smedian of 1 run |
| Llama 3.3 70B Instruct70B · 39.6 GB file | does not fit | 32 tok/smedian of 1 run |
| Nemotron 3.5 Lightning 30B-A3B30B, 3B active · 23.7 GB file | does not fit | ~175–256 tok/sestimate |
| Qwen3.6 35B-A3B35B, 3B active · 20.8 GB file | ~122–178 tok/sestimate | ~233–341 tok/sestimate |
| Ornith 1.5 35B-A3B35B, 3B active · 20.2 GB file | ~125–183 tok/sestimate | ~240–350 tok/sestimate |
| Qwen3 Coder 30B-A3B Instruct30.5B, 3.3B active · 17.3 GB file | ~116–169 tok/sestimate | ~222–324 tok/sestimate |
| Gemma 4 31B IT30.7B · 17.1 GB file | 35 tok/smedian of 1 run | 62 tok/smedian of 1 run |
| Granite 4.2 30B29.3B · 16.8 GB file | ~25–40 tok/sestimate | ~49–77 tok/sestimate |
| Qwen3.8 27B27B · 16.2 GB file | ~26–41 tok/sestimate | ~50–79 tok/sestimate |
| Gemma 4 26B-A4B IT25.2B, 3.8B active · 15.9 GB file | 119 tok/smedian of 1 run | 197 tok/smedian of 1 run |
| Qwen3.6 27B27B · 15.7 GB file | ~27–43 tok/sestimate | ~52–82 tok/sestimate |
| Devstral Small 2 24B (2512)24B · 13.3 GB file | ~32–50 tok/sestimate | ~61–96 tok/sestimate |
| gpt-oss-20b21B, 3.6B active · 10.8 GB file | 162 tok/smedian of 3 runs | 287 tok/smedian of 3 runs |
| Phi-414.7B · 8.3 GB file | ~52–81 tok/sestimate | ~99–155 tok/sestimate |
| Ministral 3 14B Reasoning (2512)13.9B · 7.7 GB file | ~56–87 tok/sestimate | ~107–167 tok/sestimate |
| Gemma 4 12B IT11.95B · 6.6 GB file | ~64–101 tok/sestimate | ~123–194 tok/sestimate |
| Qwen3.5 9B9B · 5.3 GB file | ~81–127 tok/sestimate | ~155–243 tok/sestimate |
| Granite 4.2 8B8.8B · 5.2 GB file | ~83–130 tok/sestimate | ~159–249 tok/sestimate |
| Gemma 4 E4B IT8B · 5.0 GB file | ~151–237 tok/sestimate | ~289–454 tok/sestimate |
| Qwen3 8B8.2B · 4.7 GB file | 115 tok/smedian of 1 run | 174 tok/smedian of 1 run |
| Llama 3.1 8B Instruct8B · 4.6 GB file | 122 tok/smedian of 2 runs | 144 tok/smedian of 2 runs |
| Qwen3.5 4B4B · 2.6 GB file | ~167–263 tok/sestimate | ~321–503 tok/sestimate |
Full pages: 1x RTX 3090 (used) · 1x RTX PRO 6000 Blackwell · check a different quant or context length