GPUs with 24 GB VRAM and more
Cards with at least 24 GB of video memory start at €0.30 an hour on VRAMfarm (RTX 3090). 24 GB holds a language model of about 36B parameters in 4-bit or 10B in FP16. For images and video: Flux with ControlNet, Qwen-Image, HiDream and Wan 2.2 5B video.
24 GB is the most popular size: almost every open image, video and chat model runs on it. The RTX 3090 and 4090 hold the same 24 GB; the 4090 is faster, the 3090 cheaper.
Cards with 24 GB or more, cheapest first
| GPU | Type | Memory | TFLOPS FP32 | Where | Price per hour | ≈ per month | Action |
|---|---|---|---|---|---|---|---|
| RTX 3090 | consumer | 24 GB | ≈35.6 | +15 | €0.30/h | €216 per month | Rent |
| RTX A5000 | workstation | 24 GB | ≈27.8 | €0.33/h | €238 per month | Rent | |
| L40 | data centre | 48 GB | ≈90.5 | €0.46/h | €331 per month | Rent | |
| RTX 4090 | consumer | 24 GB | ≈82.6 | +16 | €0.59/h | €425 per month | Rent |
| RTX A6000 | workstation | 48 GB | ≈38.7 | €0.72/h | €518 per month | Rent | |
| RTX 5090 | consumer | 32 GB | ≈104.8 | +15 | €0.76/h | €547 per month | Rent |
| L40S | data centre | 48 GB | ≈91.6 | +1 | €1.06/h | €763 per month | Rent |
| L4 | data centre | 24 GB | ≈30.3 | €1.37/h | €986 per month | Rent | |
| A100 | data centre | 80 GB | ≈19.5 | +2 | €1.46/h | €1,051 per month | Rent |
| RTX PRO 6000 | workstation | 96 GB | ≈125 | +8 | €2.12/h | €1,526 per month | Rent |
| H100 | data centre | 80 GB | ≈67 | +1 | €3.90/h | €2,808 per month | Rent |
| H200 | data centre | 141 GB | ≈67 | +2 | €5.43/h | €3,910 per month | Rent |
| B200 | data centre | 192 GB | ≈80 | €16.12/h | €11,606 per month | Rent |
To launch, your balance must cover one hour of the machine. You are billed by the minute for actual use.
What runs on 24 GB
Language models
Up to about 36B parameters in 4-bit (AWQ, GPTQ, GGUF Q4) or 10B in FP16, with room for a normal context. Long context and many parallel users need more. The VRAM calculator works it out for your model.
Images and video
Flux with ControlNet, Qwen-Image, HiDream and Wan 2.2 5B video.
Training
Flux and SDXL LoRAs, QLoRA of 7–8B models, LoRA of 8B with a 16-bit base on the tight side.
Typical jobs at this size
- Qwen-Image and Wan 2.2 video
- Chat models up to 32B in 4-bit
- LoRA training for Flux and SDXL
Frequently asked questions
What is the cheapest GPU with 24 GB or more?
The NVIDIA GeForce RTX 3090, from €0.30 an hour on VRAMfarm, billed by the minute.
Which LLM can I run on 24 GB?
About 36B parameters in 4-bit or 10B in FP16, with room for a normal context. For example: Llama 3.1 8B, Qwen3 14B, Qwen3 32B.
Can I combine the memory of several GPUs?
For language models, yes: vLLM and llama.cpp split a model across cards, so 2 × 24 GB can run what needs about 40 GB. For image and video models memory does not add up, one card has to hold the model.
How do I know 24 GB is enough?
Add up the weights (2 GB per billion parameters in FP16, 0.6 GB in 4-bit), the context cache and 10–15% for buffers, or use our VRAM calculator. If the model does not fit, it either fails with “CUDA out of memory” or runs much slower with offloading.
Rent 24 GB of VRAM
Top up from €10, pick a card from the list and start in a few minutes.