Text generation · served with vLLM · ↓ 90.2K downloads a month · View on Hugging Face
llm-jp/llm-jp-4.1-8b-thinking needs about 22.5 GB of GPU memory for conversations of up to 8,192 tokens. It runs on 2x RTX A4000 from $0.22/h right now; best value: 2x RTX 5060 Ti at $0.23/h.
Weights
17 GB
GPU memory needed
about 22.5 GB
Conversation length
8,192 tokens
Model allows
65,536 tokens
Memory · disk
16.6 GB · 59 GB
Architecture
LlamaForCausalLM
Licence
apache-2.0
Hardware and deploy
Name and access:llm-jp-4.1-8b-thinking · with a key
$0.23/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 llm-jp-4.1-8b-thinking need?
About 22.5 GB for conversations of up to 8,192 tokens: 17.18 GB of weights, the cache for one full-length conversation and the runtime's own memory.
What is the cheapest GPU to run llm-jp-4.1-8b-thinking?
Right now 2x RTX A4000 at $0.22 an hour; 2x RTX 5060 Ti at $0.23 an hour is the best value for its speed. Prices are live offers from GPU clouds, checked every 15 minutes.
Can llm-jp-4.1-8b-thinking run on an RTX 4090?
Yes: it needs about 22.5 GB and an RTX 4090 has 24 GB.
How do I deploy llm-jp-4.1-8b-thinking 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 chat 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 of 90% or more that download at 200 Mbit/s or more are offered: the machine fetches the model itself.