OPEN MODELS / Vision language models
Run mistral-medium-3.5:128b on a cloud GPU
mistral-medium-3.5:128b is a Vision language models model by Ollama. See how much GPU memory it needs, which GPUs it fits on today and what it costs to run it yourself, billed per second.
From the project: Mistral Medium 3.5 is the first flagship model of Mistral AI that merged instruction-following, reasoning, and coding in a single set of 128B weights.
GPUs it fits on today
About 94 GB of GPU memory: the model download (4-bit by default) plus working memory.
| GPU | Memory | Per hour | 10 hours | |
|---|---|---|---|---|
| GB10 | 119 GB | $1.19 | $11.90 | Rent |
| RTX PRO 6000 Max-Q | 96 GB | $1.93 | $19.30 | Rent |
| RTX PRO 6000 S | 96 GB | $2.73 | $27.30 | Rent |
| RTX PRO 6000 WS | 96 GB | $2.74 | $27.40 | Rent |
| RTX PRO 6000 | 96 GB | $4.21 | $42.10 | Rent |
Live starting prices from our catalog. You pay per second while the machine runs.
How to run mistral-medium-3.5:128b
- 01
Rent a GPU
Pick one of the GPUs above. Billing is per second; stop the machine and you stop paying.
- 02
Open a terminal or Jupyter
Connect over SSH or open Jupyter in your browser. PyTorch and CUDA are ready to use.
- 03
Install Ollama and run the model
Run the commands below. Ollama downloads the model and serves an OpenAI-compatible API on port 11434.
curl -fsSL https://ollama.com/install.sh | sh
ollama run mistral-medium-3.5:128bWhy run it yourself?
Run document and image understanding on your own GPU: no per-image fee, and files stay on your machine.
Questions
- How much GPU memory does mistral-medium-3.5:128b need?
- By our estimate about 94 GB for inference (128B parameters). Higher resolution, longer context or bigger batches need more.
- How much does it cost to run mistral-medium-3.5:128b?
- From $1.19 per hour on GB10, billed per second. Ten hours cost about $11.90.
- Do I need a subscription?
- No. You pay only for the time your machine runs, from your USD balance. Stop it whenever you are done.
Try it on your own GPU in minutes
Pick a GPU, open Jupyter or SSH and run any open model. You pay per second and can stop anytime; no subscription, no setup fee.
- Per-second billing in USD
- PyTorch and CUDA ready in minutes
- Rent from ChatGPT or Claude too