Downloads · 30 days
27
5% of all-time downloads
Qwen3-Coder-30B-A3B-Instruct-bnb-4b-fused
riomus/Qwen3-Coder-30B-A3B-Instruct-bnb-4b-fused
Qwen3-Coder-30B-A3B-Instruct-bnb-4b-fused is a machine learning model from riomus. 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.
Fused and quantized unsloth/Qwen3-Coder-30B-A3B-Instruct using qwen3moefused
All-time downloads
560
Public
Parameters
31.2B
48.3 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors16.1 GB · 100%
Parameter types
How the weights are stored.
U830.9B · 99%
Base models
Model card
From the Hugging Face model README
Model Card for riomus/Qwen3-Coder-30B-A3B-Instruct-bnb-4b-fused
Fused and quantized unsloth/Qwen3-Coder-30B-A3B-Instruct using qwen3_moe_fused
Because of unsloth#638 issue - model is not sharded
For training/fine-tuning/LoRA/QLoRA it is best to use just fused model riomus/Qwen3-Coder-30B-A3B-Instruct-fused
- Type
- qwen3_moe
- License
- apache-2.0
- Created
- Nov 7, 2025
- Updated
- Nov 7, 2025