Text generation · served with vLLM · ↓ 53 downloads a month · View on Hugging Face
TheBloke/Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GPTQ needs about 18 GB of GPU memory for conversations of up to 8,192 tokens. It runs on one RTX 4000 Ada from $0.22/h right now; best value: RTX 5090 at $0.64/h.
Weights
7.5 GB
GPU memory needed
about 18 GB
Conversation length
8,192 tokens
Model allows
8,192 tokens
Memory · disk
16 GB · 49 GB
Architecture
LlamaForCausalLM
Licence
other
Hardware and deploy
$0.64/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 Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GPTQ need?
About 18 GB for conversations of up to 8,192 tokens: 7.45 GB of weights, the cache for one full-length conversation and the runtime's own memory.
What is the cheapest GPU to run Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GPTQ?
Right now one RTX 4000 Ada at $0.22 an hour; RTX 5090 at $0.64 an hour is the best value for its speed. Prices are live offers from GPU clouds, checked every 15 minutes.
Can Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GPTQ run on an RTX 4090?
Yes: it needs about 18 GB and an RTX 4090 has 24 GB.
How do I deploy Wizard-Vicuna-13B-Uncensored-SuperHOT-8K-GPTQ 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 above 95% that download at 400 Mbit/s or more are offered: the machine fetches the model itself.