temaq-org/Tema_Q-X6-9B-Thinking
LoRA-style vs TokenRhythm/NeoHorse-1-9B. Looks like a merged LoRA (or a fine-tune with frozen norms): only the weight matrices of conv1d, down_proj, o_proj, out_proj changed, in 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/105, Attention 53/224, MLP 26/96, lm_head 0/1
2 derivatives checked
- mradermacher/Tema_Q-X6-9B-Thinking-i1-GGUF: Quantization
- mradermacher/Tema_Q-X6-9B-Thinking-GGUF: Same weights, converted