Gryphe/WorldSim-Opus-3.6-35B-A3B
Full fine-tune vs Qwen/Qwen3.6-35B-A3B. Fine-tune: 94% of the weights changed, across 40 of 40 layers.
Tensors changed: Embeddings 0/4, Attention 40/388, MLP 120/392, Norms 0/241, lm_head 1/1
6 derivatives checked
- bartowski/Gryphe_WorldSim-Opus-3.6-35B-A3B-GGUF: Same weights, converted
- mradermacher/WorldSim-Opus-3.6-35B-A3B-i1-GGUF: Quantization
- BlueNipples/Anansi-35B-A3B: Full fine-tune (fewer layers)
- mradermacher/WorldSim-Opus-3.6-35B-A3B-GGUF: Quantization
- Koshkasa/Gryphe_WorldSim-Opus-3.6-35B-A3B-iQ_compact_APEX-GGUF: Quantization
- Cyclone-Labs/Qwen3.6-Fallen-Fabulist-35B-A3B-heretic: Full fine-tune