unsloth/Qwen3-4B-Thinking-2507
Same weights, repacked vs Qwen/Qwen3-4B-Thinking-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
27 derivatives checked
- TeichAI/Qwen3-4B-Thinking-2507-GPT-5.1-Codex-Max-Distill: LoRA-style
- magiccodingman/Qwen3-4B-Thinking-2507-Unsloth-MagicQuant-Hybrid-GGUF: Quantization
- electron271/graig-alpha: LoRA-style
- TeichAI/Qwen3-4B-Thinking-2507-Claude-4.5-Opus-High-Reasoning-Distill: LoRA-style
- TeichAI/Qwen3-4B-Thinking-MiniMax-M2.1-Coder: LoRA-style
- TeichAI/Qwen3-4B-Thinking-2507-GPT-5.2-High-Reasoning-Distill: LoRA-style
- TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Distill: LoRA-style
- TeichAI/Qwen3-4B-Thinking-2507-Gemini-2.5-Flash-Lite-Preview-Distill: LoRA-style
- TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Pro-Preview-High-Reasoning-Distill: LoRA-style
- TeichAI/Qwen3-4B-Thinking-2507-Gemini-3-Flash-VIBE: LoRA-style
- khazarai/Qwen3-4B-Qwen3.6-plus-Reasoning-Distilled: LoRA-style
- TeichAI/Qwen3-4B-Thinking-2507-Kimi-K2-Thinking-Distill: LoRA-style
- khazarai/Qwen3-4B-Kimi2.5-Reasoning-Distilled: LoRA-style
- TeichAI/Qwen3-4B-Thinking-2507-MiniMax-M2.1-Distill: LoRA-style
- Liontix/Qwen3-4B-Thinking-2507-Gemini-2.5-Pro-Distill: LoRA-style
- TeichAI/Qwen3-4B-Thinking-2507-Command-A-Reasoning-Distill: LoRA-style
- TeichAI/Qwen3-4B-Thinking-2507-MiMo-V2-Flash-Distill: LoRA-style
- Jackrong/DASD-4B-Thinking-2507-GRPO-v2: LoRA-style
- TeichAI/Qwen3-4B-Thinking-2507-GPT-5-Codex-Distill: LoRA-style
- fireworks1231/qwen3-4b-2504-1400step: LoRA-style
- Cannae-AI/Gpt-oss-120B-Qwen3-Distill: LoRA-style
- Ba2han/Qwen3-4B-2507-Geminized-v1: LoRA-style
- qingy2024/Gem-4B-Thinking: LoRA-style
- sanjitkverma/UIGEN-X-4B-STD-LoRA: LoRA-style
- smirki/UIGEN-X-4B-SFT-LoRA-128: LoRA-style
- HappyAIUser/AtmaSiddhiGPTv26: LoRA-style
- debasmitadasgupta/tony-seba-qwen3-4b: LoRA-style
4 other repos hold byte-for-byte identical weight files.