Downloads · 30 days
78
4% of all-time downloads
Qwen3-Coder-30B-A3B-Instruct-4bit-GPTQ
pramjana/Qwen3-Coder-30B-A3B-Instruct-4bit-GPTQ
Qwen3-Coder-30B-A3B-Instruct-4bit-GPTQ is a text generation model from pramjana. Use it when you need the model to write or continue text. It is set up for transformers. The card lists the license as apache-2.0.
This is my (first) attempt at quantizing this Qwen3 model (Qwen/Qwen3-Coder-30B-A3B-Instruct) using auto-round, like so:
All-time downloads
1.9K
Public
Parameters
623M
16.9 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.9 GB · 100%
Parameter types
How the weights are stored.
I3229.9B · 98%
Try a prompt
Base models
Model card
From the Hugging Face model README
This is my (first) attempt at quantizing this Qwen3 model (Qwen/Qwen3-Coder-30B-A3B-Instruct) using auto-round, like so:
auto-round-light --model "Qwen/Qwen3-Coder-30B-A3B-Instruct" --scheme "W4A16" --format "auto_gptq" --output_dir "./Quantized" --model_dtype fp16
- Task
- Text Generation
- Library
- transformers
- Type
- qwen3_moe
- License
- apache-2.0
- Created
- Oct 20, 2025
- Updated
- Oct 30, 2025