Embeddings (features) · served with vLLM · ↓ 5.6K downloads a month · View on Hugging Face
microsoft/harrier-oss-v1-27b needs about 66.3 GB of GPU memory. It runs on one RTX PRO 6000 from $1.16/h right now.
Weights
54 GB
GPU memory needed
about 66.3 GB
Model allows
131,072 tokens
Memory · disk
85 GB · 100 GB
Architecture
Gemma3TextModel
Licence
mit
Hardware and deploy
$1.16/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 harrier-oss-v1-27b need?
About 66.3 GB: 54.02 GB of weights and the runtime's own memory.
What is the cheapest GPU to run harrier-oss-v1-27b?
Right now one RTX PRO 6000 at $1.16 an hour. Prices are live offers from GPU clouds, checked every 15 minutes.
Can harrier-oss-v1-27b run on an RTX 4090?
Not on one: it needs about 66.3 GB and an RTX 4090 has 24 GB. Use a bigger GPU, or a smaller (quantized) version of the model.
How do I deploy harrier-oss-v1-27b 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.