unsloth/Qwen3-14B
Same weights, repacked vs Qwen/Qwen3-14B. Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/120, Attention 0/160, lm_head 0/1
13 derivatives checked
- TeichAI/Qwen3-14B-Claude-4.5-Opus-High-Reasoning-Distill: LoRA-style
- mlx-community/Qwen3-14B-4bit-AWQ: Quantization
- TeichAI/Qwen3-14B-GPT-5.2-High-Reasoning-Distill: LoRA-style
- TeichAI/Qwen3-14B-Gemini-3-Pro-Preview-High-Reasoning-Distill: LoRA-style
- TeichAI/Qwen3-14B-DeepSeek-v3.2-Speciale-Distill: LoRA-style
- TeichAI/Qwen3-14B-Polaris-Alpha-Distill: LoRA-style
- shadowlilac/OpenGemini-Flash: LoRA-style
- Davletovarch/logos-v1-merged: LoRA-style
- NaruseShiroha/capybara-14b: LoRA-style
- anaspro/Shako-iraqi-8B-it: LoRA-style
- KhyontekAI/Qwen3-14B-Eng-to-Asm: LoRA-style
- Samarth2511/Qwen3-14B-KE-strict-r32-full: LoRA-style
- Samarth2511/Qwen3-14B-KE-indecisive-r32-full: LoRA-style
7 other repos hold byte-for-byte identical weight files.