janhq/Jan-v1-4B
Full fine-tune vs Qwen/Qwen3-4B-Thinking-2507. Fine-tune: 90% of the weights changed, across 36 of 36 layers.
Tensors changed: Embeddings 0/1, Norms 111/145, MLP 108/108, Attention 144/144
8 derivatives checked
- janhq/Jan-v1-4B-GGUF: Quantization
- DavidAU/Qwen3-Jan-V1-4B-Grand-Horror-Day1-to-Day7-Evolved-Imatrix-GGUF: Quantization
- bartowski/janhq_Jan-v1-4B-GGUF: Same weights, converted
- mradermacher/Jan-v1-4B-i1-GGUF: Quantization
- DevQuasar/janhq.Jan-v1-4B-GGUF: Same weights, converted
- mradermacher/Jan-v1-4B-GGUF: Same weights, converted
- DavidAU/Qwen3-Jan-v1-256k-ctx-6B-Brainstorm20x: Partial fine-tune (fewer layers)
- ZarfixAI/ZarfixAICerdas1.0: Identical copy
2 other repos hold byte-for-byte identical weight files.