Hardware
Dual RTX 3090, 48 GB
The classic 70B Q4 rig. Two cards, more hassle, enough memory.
Memory
48 GB VRAMBandwidth
1872 GB/sBandwidth source is not stored.
Price
$6,054€5,408
price as of 16 Oct 2026
128 GB DDR4 (estimate): $2,754€2,460. From the 16 Oct 2026 fact-check.
rest of system (estimate): $560€500. The total is the GPU price plus the RAM line plus this estimate. It is not a checked system price.
price unverifiedGPU line is 2× the used median €1,224 (€2,448), labelled used, from pcprice.watch (https://www.pcprice.watch/gpu-buying-guide/rtx-3090-price-used-and-specs). 128 GB DDR4 (estimate) €2,460, from the 16 Oct 2026 fact-check. Rest of system (estimate) €500. Other parts from €500 in that fact-check. Not a shop listing. The total is the GPU price plus the RAM line plus that rest estimate. It is not a checked system price.
Parts in the catalog
- 2× GeForce RTX 3090 24GB, used
- 128 GB DDR4 (estimate): €2,460. from the 16 Oct 2026 fact-check.
- Rest of system (estimate): €500. Other parts from €500 in that fact-check. Not a shop listing.
- Ryzen 9 5900X or similar
- 1200W PSU, a case that can breathe
Which models fit
Estimate at 8,192 tokens, or the model's maximum when that is shorter. full means the formula fits in usable memory. offload means GPU plus system RAM. no means it does not fit. This is not a measured file.
| Model | Q4Q4_K_Mestimate | Q5Q5 (~0.71 bytes/param)estimate | Q8Q8estimate | FP16FP16estimate |
|---|---|---|---|---|
| Llama 3.2 3B | full | full | full | full |
| Llama 3.1 8B | full | full | full | full |
| Mistral 7B v0.3 | full | full | full | full |
| Gemma 2 9B | full | full | full | full |
| Qwen2.5 14B | full | full | full | full |
| Phi-4 14B | full | full | full | full |
| Gemma 2 27B | full | full | full | offload |
| Qwen2.5 32B | full | full | full | offload |
| Llama 3.3 70B | full | offload | offload | offload |
| Qwen2.5 72B | offload | offload | offload | offload |
| DeepSeek-R1-Distill 70B | full | offload | offload | offload |
We'll match you with vetted providers