by openai-community
⬇ 29.8M♥ 3.9K
Qwen3.5-4B-QuantStudy-GPTQ-W4A16
- Task
- Text generation
- Category
- Language
- License
- Apache 2.0
- Commercial use
- Yes
Permissive license: commercial use is allowed; keep the copyright and license notice. - Size
- About 4 billion parameters
- Memory to load
- ~3 GB (estimate)
- Format
- GPTQ
- Runs on
- GPU
- Access
- Open download
- Downloads (last 30 days)
- 0
- Likes
- 0
- Last updated
- September 22, 2026
How to run it
These are 4-bit quantized weights for NVIDIA GPUs; load them with a library that supports GPTQ, such as vLLM or Hugging Face Transformers.
Plan for roughly 3 GB of memory to load it (our estimate from its size and format).
The model card on Hugging Face has the exact usage code.
Where to run it
On your own computer, free
Both load GGUF builds; for other formats, look for a GGUF version of this model.
In the cloud
Needs about 3 GB: a 24 GB GPU such as an RTX 4090 or RTX A5000 is enough.
- RunPod · rent a GPU by the hour (affiliate link)
Related text generation models
Data from Hugging Face's public API, last checked September 22, 2026. Downloads are Hugging Face's count for the last 30 days.