szybkie-ai/jeb-35b-a3b

Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 93% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 0/5, Attention 190/392, MLP 80/399, Norms 0/247, lm_head 0/1, other 0/1

2 derivatives checked

• mradermacher/jeb-35b-a3b-GGUF: Quantization
• szybkie-ai/jeb-35b-a3b-gguf: Quantization

On the Hub · Downloads on Model Pulse