Neura-Tech-AI/Neuron-4B-Instruct
Same weights, repacked vs Qwen/Qwen3-4B-Instruct-2507. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144
6 derivatives checked
- mradermacher/Neuron-V2-4B-Instruct-i1-GGUF: Quantization
- Neuron-AI-Labs/Neuron-12x4B-EXP: MoE built from dense models
- Neura-Tech-AI/Neuron-4B-HeavyThinking: LoRA-style
- mradermacher/Neuron-V2-4B-Instruct-GGUF: Same weights, converted
- Neura-Tech-AI/Neuron-46x4B: Same weights, repacked
- Neura-Tech-AI/Neuron-6x4B-Instruct: Same weights, repacked