Qwen3-4B-Nyx-V3

Qwen3-4B-Nyx-V3 is a merge of the following models using mergekit:

bunnycore/Qwen3-4B-Nyx-V1
bunnycore/Qwen3-4B-RP-V3

🧩 Configuration


models:
  - model: bunnycore/Qwen3-4B-Nyx-V1
    parameters:
      density: 0.5
      weight: 0.5
  - model: bunnycore/Qwen3-4B-RP-V3
    parameters:
      density: 0.5
      weight: 0.5
merge_method: ties
base_model: mlabonne/Qwen3-4B-abliterated+bunnycore/Qwen3-4B-Steer-lora
parameters:
  normalize: true
dtype: float16

Downloads last month: 3

Safetensors

Model size

4B params

Tensor type

F16

Inference Providers NEW

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

Model tree for bunnycore/Qwen3-4B-Nyx-V3.1-Test

bunnycore/Qwen3-4B-RP-V3

bunnycore/Qwen3-4B-Steer-lora

Merge model

this model

Quantizations

1 model