bingleai/FableOpus-9B-Linear

Partial fine-tune vs Jackrong/Qwen3.5-9B-Claude-4.6-Opus-Reasoning-Distilled. Partial change: 84% of the weights changed (attention, lm_head, mlp, norms), in 32 of 32 layers.

Tensors changed: lm_head 1/1, Embeddings 0/4, MLP 96/208, Attention 176/332, Norms 58/215

1 derivatives checked

• mradermacher/FableOpus-9B-Linear-GGUF: Same weights, converted

On the Hub · Downloads on Model Pulse