unsloth/Qwen3-4B-Instruct-2507
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
37 derivatives checked
- myfi/parser_model_ner_4.12: LoRA-style
- DexopT/Qwen3-4B-Cybersecurity: LoRA-style
- abdullahalbaki/mgi-assistant-v1-qwen3-4b: LoRA-style
- Ihteshamstar/qwen3-4b-cuad-extractor: LoRA-style
- basilmh25/qwen_fine-tune_Cybersecurity: Quantization
- WasamiKirua/Qwen3-4B-Alucard: LoRA-style
- ChisatoY/dolas-zh-finetuned: LoRA-style
- magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-Hybrid-GGUF: Quantization
- principled-intelligence/scope-guard-4B-q-2601: LoRA-style
- bingbangboom/dolus-v3-ep1-instruct-GGUF: Full fine-tune
- magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MagicQuant-v2-GGUF: Quantization
- aliRafik/qwen3_4B_capybara_full_ft: Full fine-tune
- electron271/graig-experiment-3: LoRA-style
- WasamiKirua/Qwen3-4B-Alucard-GGUF: Full fine-tune
- NaruseShiroha/capybara-math-smol-4.1B-2509-preview-GGUF: LoRA-style
- electron271/graig-experiment-2: LoRA-style
- NaruseShiroha/capybara-math-smol-WebCoder: LoRA-style
- ahmetggg/Luck-Qwen3-4b-Code-FineTune: LoRA-style
- mrankitvish577/Qwen3-4B-Instruct-2507-GGUF: Full fine-tune
- TeichAI/Qwen3-4B-Instruct-2507-Polaris-Alpha-Distill-GGUF: LoRA-style
- magiccodingman/Qwen3-4B-Instruct-2507-Unsloth-MXFP4-Hybrid-GGUF: Quantization
- NaruseShiroha/capybara-math-smol-4.1B-2508GGUF: LoRA-style
- TeichAI/Qwen3-4B-Instruct-2507-Claude-Opus-3-Distill: LoRA-style
- TeichAI/Qwen3-4B-Instruct-2507-Claude-Haiku-4.5-Distill: LoRA-style
- ragib01/Qwen3-4B-customer-support: LoRA-style
- TeichAI/Qwen3-4B-Instruct-2507-Gemini-3-Pro-Preview-Distill: LoRA-style
- fireworks1231/lightning-2510: LoRA-style
- TeichAI/Qwen3-4B-Instruct-2507-Polaris-Alpha-Distill: LoRA-style
- fireworks1231/qwen3-4b-2509-grpo-b: LoRA-style
- blah7/My-intelligent-true-qwen-RL: LoRA-style
37 other repos hold byte-for-byte identical weight files.