OPEN MODELS / Language models (LLM)
Run DeepSeek-V2-Lite-Chat-IMat-GGUF on a cloud GPU
DeepSeek-V2-Lite-Chat-IMat-GGUF is a Language models (LLM) model by legraphista. 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 13 GB for inference with GGUF weights, including working memory. Real use depends on resolution, batch size and context length.
| GPU | Memory | Per hour | 10 hours | |
|---|---|---|---|---|
| RTX A4000 | 16 GB | $0.21 | $2.10 | Rent |
| RTX 5060 Ti | 16 GB | $0.23 | $2.30 | Rent |
| RTX 2080 Ti | 22 GB | $0.25 | $2.50 | Rent |
| Tesla V100 | 16 GB | $0.25 | $2.50 | Rent |
| Q RTX 5000 | 16 GB | $0.27 | $2.70 | Rent |
Live starting prices from our catalog. You pay per second while the machine runs.
How to run DeepSeek-V2-Lite-Chat-IMat-GGUF
- 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 "huggingface_hub[cli]"
huggingface-cli download legraphista/DeepSeek-V2-Lite-Chat-IMat-GGUF --local-dir ./model --include "*Q4_K_M*"
# llama.cpp: ./llama-server -m ./model/*.gguf --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 DeepSeek-V2-Lite-Chat-IMat-GGUF need?
- By our estimate about 13 GB for inference (16B parameters). Higher resolution, longer context or bigger batches need more.
- How much does it cost to run DeepSeek-V2-Lite-Chat-IMat-GGUF?
- From $0.21 per hour on RTX A4000, billed per second. Ten hours cost about $2.10.
- 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