Qwen-3-4B-Refine

Qwen-3-4B-Refine is a merge of the following models using mergekit:

🧩 Configuration

base_model: unsloth/Qwen3-4B+bunnycore/Qwen-3-4b-lora_model
dtype: bfloat16
merge_method: passthrough
models:
  - model: unsloth/Qwen3-4B+bunnycore/Qwen-3-4b-lora_model

Downloads last month: 4

Safetensors

Model size

3.64B params

Tensor type

BF16

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support