GPUs with 16 GB VRAM and more
Cards with at least 16 GB of video memory start at €0.16 an hour on VRAMfarm (RTX 4060 Ti). 16 GB holds a language model of about 24B parameters in 4-bit or 7B in FP16. For images and video: SDXL and Flux in fp8, with room for a LoRA or two.
16 GB is where Flux becomes comfortable and 14B chat models fit in 4-bit. The RTX 4060 Ti 16 GB and RTX A4000 are cheap ways to get there.
Cards with 16 GB or more, cheapest first
| GPU | Type | Memory | TFLOPS FP32 | Where | Price per hour | ≈ per month | Action |
|---|---|---|---|---|---|---|---|
| RTX 4060 Ti | consumer | 16 GB | ≈22.1 | +5 | €0.16/h | €115 per month | Rent |
| RTX A4000 | workstation | 16 GB | ≈19.2 | +1 | €0.18/h | €130 per month | Rent |
| RTX 5070 Ti | consumer | 16 GB | ≈43.9 | +3 | €0.24/h | €173 per month | Rent |
| RTX 3090 | consumer | 24 GB | ≈35.6 | +15 | €0.30/h | €216 per month | Rent |
| RTX 4080 | consumer | 16 GB | ≈48.7 | +7 | €0.31/h | €223 per month | Rent |
| RTX A5000 | workstation | 24 GB | ≈27.8 | €0.33/h | €238 per month | Rent | |
| RTX 5080 | consumer | 16 GB | ≈56.3 | +7 | €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 16 GB
Language models
Up to about 24B parameters in 4-bit (AWQ, GPTQ, GGUF Q4) or 7B 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
SDXL and Flux in fp8, with room for a LoRA or two.
Training
LoRA for SDXL and, with optimisations, Flux; QLoRA of 7–8B models with short sequences.
Typical jobs at this size
- SDXL and Flux in fp8
- Chat models up to 14B in 4-bit
- Whisper and text to speech
Frequently asked questions
What is the cheapest GPU with 16 GB or more?
The NVIDIA GeForce RTX 4060 Ti 16GB, from €0.16 an hour on VRAMfarm, billed by the minute.
Which LLM can I run on 16 GB?
About 24B parameters in 4-bit or 7B in FP16, with room for a normal context. For example: Llama 3.1 8B, Qwen3 14B.
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 16 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 16 GB of VRAM
Top up from €10, pick a card from the list and start in a few minutes.