migtissera/Synthia-4-27B

Full fine-tune vs Qwen/Qwen3.8-27B. Fine-tune: 92% of the weights changed, across 64 of 64 layers.

Tensors changed: Norms 0/325, Attention 208/560, MLP 192/307, Embeddings 0/5, lm_head 1/1, other 0/1

3 derivatives checked

• mradermacher/Synthia-4-27B-i1-GGUF: Quantization
• migtissera/Synthia-4-27B-GGUF: Same weights, converted
• mradermacher/Synthia-4-27B-GGUF: Quantization

On the Hub · Downloads on Model Pulse