OmniEdu/Omni-Edu-27B

Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 98% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 144/319, Attention 378/556, MLP 192/304, Embeddings 1/4, lm_head 1/1

1 derivatives checked

• mradermacher/Omni-Edu-27B-GGUF: Quantization

2 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse