datajuicer/Juicer-35B-A3B
Partial fine-tune (fewer layers) vs Qwen/Qwen3.6-35B-A3B. Qwen/Qwen3.6-35B-A3B matches part of datajuicer/Juicer-35B-A3B (946 of its 31666 tensors; the rest of datajuicer/Juicer-35B-A3B has no counterpart). On the shared part: Partial change: 85% of the weights changed (attention, embeddings, lm_head, mlp, norms), in 40 of 40 layers.
Tensors changed: Embeddings 1/4, Attention 231/388, MLP 200/312, Norms 91/241, lm_head 1/1
2 derivatives checked
- mradermacher/Juicer-35B-A3B-i1-GGUF: Quantization
- mradermacher/Juicer-35B-A3B-GGUF: Quantization