Blackfrost-Research/M.O.G.-SEC-27B-1M-CTX-BF16
LoRA-style vs Qwen/Qwen3.8-27B. 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, out_proj, q_proj, up_proj, v_proj changed, in 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/325, Attention 112/560, MLP 192/307, Embeddings 0/5, lm_head 0/1, other 0/1
4 derivatives checked
- Blackfrost-Research/M.O.G.-SEC-27B-1M-CTX-GGUF: Not comparable yet
- mradermacher/M.O.G.-SEC-27B-1M-CTX-BF16-GGUF: Quantization
- mradermacher/M.O.G.-SEC-27B-1M-CTX-BF16-i1-GGUF: Quantization
- Blackfrost-Research/M.O.G.-SEC-27B-1M-CTX-NVFP4: Quantization
1 other repos hold byte-for-byte identical weight files.