OPEN MODELS / Language models (LLM)
Run K2-Horizon-375B-A23B on a cloud GPU
K2-Horizon-375B-A23B is a Language models (LLM) model by IFM. See how much GPU memory it needs, which GPUs it fits on today and what it costs to run it yourself, billed per second.
GPUs it fits on today
Our estimate is about 912 GB for inference with BF16 weights, including working memory. Real use depends on resolution, batch size and context length. With 4-bit quantization it needs about 275 GB.
| GPU | Memory | Per hour | 10 hours | |
|---|---|---|---|---|
| 16× A100 | 1280 GB | $42.56 | $425.60 | Rent |
| 8× H200 | 1120 GB | $46.08 | $460.80 | Rent |
| 4× B300 | 1076 GB | $68.24 | $682.40 | Rent |
| 8× B200 | 1432 GB | $100.24 | $1,002.40 | Rent |
Live starting prices from our catalog. You pay per second while the machine runs.
How to run K2-Horizon-375B-A23B
- 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
Download and run the model
Run the commands below. The weights download straight from Hugging Face to your machine.
pip install -U vllm
vllm serve IFM/K2-Horizon-375B-A23B --host 0.0.0.0 --port 8000Why run it yourself?
Your own LLM server has no per-token bill and no rate limit, and your data stays private. Pick a GPU by memory and serve the model with vLLM.
Questions
- How much GPU memory does K2-Horizon-375B-A23B need?
- By our estimate about 912 GB for inference (379B parameters). Higher resolution, longer context or bigger batches need more.
- How much does it cost to run K2-Horizon-375B-A23B?
- From $42.56 per hour on 16× A100, billed per second. Ten hours cost about $425.60.
- 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