Text generation · served with vLLM · ↓ 7.4K downloads a month · View on Hugging Face
tzervas/qwen2.5-coder-32b-bitnet-1.58b needs about 16 GB of GPU memory for conversations of up to 8,192 tokens. It runs on 2x RTX 3060 from $0.18/h right now; best value: RTX 5090 at $0.62/h.
Weights
10 GB
GPU memory needed
about 16 GB
Conversation length
8,192 tokens
Model allows
32,768 tokens
Memory · disk
16 GB · 52 GB
Architecture
Qwen2ForCausalLM
Licence
apache-2.0
Versions of Qwen2.5 32B
The same model packaged differently: a quantized version needs less GPU memory and runs on a cheaper machine.
Name and access:qwen2.5-coder-32b-bitnet-1.58b · with a key
$0.62/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 qwen2.5-coder-32b-bitnet-1.58b need?
About 16 GB for conversations of up to 8,192 tokens: 10.24 GB of weights, the cache for one full-length conversation and the runtime's own memory.
What is the cheapest GPU to run qwen2.5-coder-32b-bitnet-1.58b?
Right now 2x RTX 3060 at $0.18 an hour; RTX 5090 at $0.62 an hour is the best value for its speed. Prices are live offers from GPU clouds, checked every 15 minutes.
Can qwen2.5-coder-32b-bitnet-1.58b run on an RTX 4090?
Yes: it needs about 16 GB and an RTX 4090 has 24 GB.
How do I deploy qwen2.5-coder-32b-bitnet-1.58b 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.