GestaltLabs/Ornstein3.6-35B-A3B
LoRA-style vs unsloth/Qwen3.6-35B-A3B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of down_proj, gate_proj, k_proj, o_proj, q_proj, up_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Attention 40/388, MLP 120/392, Norms 0/241, lm_head 0/1
3 derivatives checked
- mradermacher/Ornstein3.6-35B-A3B-i1-GGUF: Quantization
- mradermacher/Ornstein3.6-35B-A3B-GGUF: Quantization
- Nishant2414/Ornstein3.6-35B-A3B-GGUF: Quantization