GPUs with 141 GB VRAM and more
Cards with at least 141 GB of video memory start at €5.43 an hour on VRAMfarm (H200). 141 GB holds a language model of about 213B parameters in 4-bit or 64B in FP16. For images and video: any open image or video model, several of them in memory at once.
141 GB on the H200 and 192 GB on the B200 fit the largest open models on one card, including 70B in FP16 and big mixture-of-experts models in 4-bit.
Cards with 141 GB or more, cheapest first
| GPU | Type | Memory | TFLOPS FP32 | Where | Price per hour | ≈ per month | Action |
|---|---|---|---|---|---|---|---|
| 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 141 GB
Language models
Up to about 213B parameters in 4-bit (AWQ, GPTQ, GGUF Q4) or 64B 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
Any open image or video model, several of them in memory at once.
Training
QLoRA of 70B, LoRA of 32B with a 16-bit base, full fine-tuning of 8B with an 8-bit optimiser.
Typical jobs at this size
- 235B mixture-of-experts in 4-bit
- Training with large batches
- The biggest open models on one card
Frequently asked questions
What is the cheapest GPU with 141 GB or more?
The NVIDIA H200, from €5.43 an hour on VRAMfarm, billed by the minute.
Which LLM can I run on 141 GB?
About 213B parameters in 4-bit or 64B in FP16, with room for a normal context. For example: Qwen3 14B, Qwen3 32B, Llama 3.3 70B.
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 141 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 141 GB of VRAM
Top up from €10, pick a card from the list and start in a few minutes.