Embeddings (features) · served with vLLM · ↓ 16.8K downloads a month · View on Hugging Face
CofeAI/Tele-FLM needs about 128.3 GB of GPU memory. It runs on one Nvidia H200 from $4.53/h right now.
Weights
106 GB
GPU memory needed
about 128.3 GB
Model allows
4,096 tokens
Memory · disk
162.5 GB · 157 GB
Architecture
TeleFLMModel
Licence
apache-2.0
Hardware and deploy
$4.53/h from your balance while it runs, billed by the hour; stop it from its page. GridPup rents the machine, which downloads the model from Hugging Face (usually ready in 10 to 15 minutes), and gives you an https address, keys and a Playground.
Questions
How much GPU memory does Tele-FLM need?
About 128.3 GB: 105.65 GB of weights and the runtime's own memory.
What is the cheapest GPU to run Tele-FLM?
Right now one Nvidia H200 at $4.53 an hour. Prices are live offers from GPU clouds, checked every 15 minutes.
Can Tele-FLM run on an RTX 4090?
Not on one: it needs about 128.3 GB and an RTX 4090 has 24 GB. Use a bigger GPU, or a smaller (quantized) version of the model.
How do I deploy Tele-FLM as an API?
Pick a machine on its GridPup page and press Deploy: GridPup rents the GPU, downloads the model from Hugging Face and serves it at an https address with keys and OpenAI's embeddings API, billed by the hour.
Prices are per hour for the whole machine and its disk, right now. Speed is Vast's DLPerf score of the machine, relative to the cheapest. Best value: the most speed per dollar. Only machines with a Vast reliability above 95% that download at 400 Mbit/s or more are offered: the machine fetches the model itself.