Enriqueag26/OmniCare-Qwen3-VL-30B-A3B
LoRA-style vs unsloth/Qwen3-VL-30B-A3B-Instruct. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of gate, k_proj, o_proj, q_proj, v_proj changed, in 48 of 48 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/4, Norms 0/309, MLP 48/268, Attention 192/300, lm_head 0/1
1 derivatives checked
- mradermacher/OmniCare-Qwen3-VL-30B-A3B-GGUF: Quantization