Jackrong/Qwopus3.6-27B-Coder
LoRA-style vs Jackrong/Qwopus3.6-27B-v2. 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: Embeddings 0/5, MLP 192/307, Attention 112/560, lm_head 0/1, Norms 0/325, other 0/1
11 derivatives checked
- Jackrong/Qwopus3.6-27B-Coder-Compat-MTP-GGUF: Quantization
- LeaderboardModel1/Qwopus3.6-27B-Coder-AutoRound-W4A16-RTN: Quantization
- maci0/Qwopus3.6-27B-Coder-NVFP4: Quantization
- lemuralabs/Qwen3.6-27B-Coder-uncensored-MXFP8: Quantization
- mradermacher/Qwopus3.6-27B-Coder-i1-GGUF: Quantization
- mradermacher/Qwopus3.6-27B-Coder-GGUF: Quantization
- lemuralabs/Qwen3.6-27B-Coder-uncensored-MXFP4: Quantization
- 8sp4rk/Qwopus3.6-27B-Coder-heretic: Abliterated
- nom666/Qwopus3.6-27B-Coder-MTPLX-4bit-Speed: Quantization
- pearsonkyle/Qwopus3.6-27B-Coder-imatrix-MTP-GGUF: Quantization
- cpatonn/Qwopus3.6-27B-Coder-AWQ-INT4: Quantization