Downloads · 30 days
12
11% of all-time downloads
Qwen3-Coder-pruned-20B-A3B-bnb-4bit
Pinkstackorg/Qwen3-Coder-pruned-20B-A3B-bnb-4bit
Qwen3-Coder-pruned-20B-A3B-bnb-4bit is a machine learning model from Pinkstackorg. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
This is a 4bit bnb quant of the original model.
All-time downloads
112
Public
Parameters
19.8B
11.2 GB on disk
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors11.2 GB · 100%
Parameter types
How the weights are stored.
U819.8B · 97%
Base models
Model card
From the Hugging Face model README
This is a 4bit bnb quant of the original model.
This is a layer-wise pruned variant of cerebras/Qwen3-Coder-REAP-25B-A3B resulting in a ~20B model with ~3B active parameters. It has not been fine-tuned yet.
Prune info: Original model: 48 layers New model: 38 Layers
result: Similar model, it MUST be fine-tuned before usage as current performance is non-ideal. While it can absolutely be used as is, fine-tuning is needed.
- Type
- qwen3_moe
- License
- apache-2.0
- Created
- Jan 3, 2026
- Updated
- Jan 4, 2026