NVIDIA (used) · GPU PC
RTX 3090 24GB (Used) Build
Best budget 24GB option, used market
- 24 GBGPU memory (VRAM)
- 14Bfits in memory (Q4, 8k)
- 14Bpractical (estimate)
- 500 Wmax draw
- ~€1,200indicative price
What can it run?
Pick a job or a model size. The bar compares what it needs with this machine's usable memory.
- Model weights
- Context cache
- Runtime + extras (Whisper, embeddings)
How we calculate this
Weights = parameters × bits per weight / 8 (Q4_K_M ≈ 4.85; Q8_0 ≈ 8.5). Cache = context tokens × the reference model's per-token size (layers × KV heads × head size × 2 × 2 bytes). Plus 1.5 GB of runtime. Usable memory = total minus what the system keeps (3–6 GB on shared memory, 0.5 GB on a GPU). Comfortable = fits in 85%. It is a ±20% estimate: measure it on your machine before you decide. How to pick the GGUF file
When does it beat the cloud?
Set your usage. We compare the purchase plus electricity with what you would pay a cloud API.
| Month | Own hardware | Cloud |
|---|
- Own hardware (purchase + electricity)
- Cloud API
Assumptions: €0.25/kWh (Spain average, editable), USD 1 = €0.92, 3 input tokens per output token, and the machine at maximum draw for every hour it is on (worst case). API prices verified 2026-09-09. Your time and maintenance are not included. Note: the cloud side is a frontier model and here you would run a smaller open one; this compares cost, not quality.
Learn with this machine
- Local AI Hardware Catalogue 2026: What to Buy at Each BudgetA buying catalogue for local AI by budget tier, with third-party benchmarks for every device and five questions that tell you which tier you actually need.
- ComfyUI ControlNet Tutorial: Guided Image GenerationStep-by-step guide to using ControlNet with Canny edge detection in ComfyUI. Generate images that follow the structure of a reference photo — locally, for free.
- Fine-Tune AI Models on Your Own Hardware: The LoRA Guide for SMEsYou don't need a data center to customize AI models. How LoRA and QLoRA let a Mac or a single consumer GPU fine-tune a 7B model, with MLX and Unsloth steps.
- GGUF Quantization: Pick the Right File for Your MachineHow to read a GGUF file name, choose between Q4_K_M, Q5 and Q8 for the memory you have, and measure speed, memory and quality yourself with three commands.
Skip it if…
- it will run all day in an office: it draws up to 500 W and a desktop GPU is not quiet.
- you need 70B models: they do not fit in this much GPU memory.
Specs and where the numbers come from
| CPU | Any modern CPU |
|---|---|
| GPU | RTX 3090 24GB |
| NPU | N/A (CUDA cores) |
| Memory | 24 GB (GPU memory (VRAM)); usable by the model ≈ 23.5 GB |
| Speed | 80 tok/s with 30B vendor or community estimate, not measured by us |
| Price | ~€1,200 indicative, checked 2026-09-19; check the live price in the shop |
We only call something "measured" when it ran on our machines. Editorial policy