armand0e/Qwen3.6-35B-A3B-Fable-5-Distill

Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 94% of the weights changed, across 40 of 40 layers.

Tensors changed: Embeddings 0/5, Attention 190/392, MLP 240/399, Norms 0/247, lm_head 0/1, other 0/1

3 derivatives checked

• mradermacher/Qwen3.6-35B-A3B-Fable-5-Distill-GGUF: Quantization
• mradermacher/Qwen3.6-35B-A3B-Fable-5-Distill-i1-GGUF: Quantization
• vcsbrito/Qwen3.6-35B-A3B-Fable-5-Distill-4bit-DWQ-Vision-MLX: Quantization

On the Hub · Downloads on Model Pulse