JetBrains/Qwen3.8-3.6-27B-blend
Full fine-tune vs Qwen/Qwen3.6-27B. Fine-tune: 100% of the weights changed, across 64 of 64 layers.
Tensors changed: Embeddings 5/5, MLP 307/307, Attention 558/560, lm_head 1/1, Norms 325/325, other 1/1
6 derivatives checked
- JetBrains/Qwen3.8-3.6-27B-blend-GGUF: Quantization
- bartowski/JetBrains-Qwen3.8-3.6-27B-blend-GGUF: Same weights, converted
- mradermacher/Qwen3.8-3.6-27B-blend-i1-GGUF: Quantization
- mradermacher/Qwen3.8-3.6-27B-blend-GGUF: Quantization
- JetBrains/Qwen3.8-3.6-27B-blend-MLX-4bit: Quantization
- JetBrains/Qwen3.8-3.6-27B-blend-MTP-MLX-4bit: Quantization
1 other repos hold byte-for-byte identical weight files.