Jackrong/Qwopus3.6-35B-A3B-Coder
LoRA-style vs Jackrong/Qwopus3.6-35B-A3B-v1. 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 39 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/5, Attention 40/392, MLP 120/399, Norms 0/247, lm_head 0/1, other 0/1
16 derivatives checked
- pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder-GGUF: Full fine-tune
- nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-KAT-Coder-C-qx86-hi-mlx: Quantization
- mudler/Qwopus3.6-35B-A3B-Coder-APEX-GGUF: Quantization
- mudler/Qwopus3.6-35B-A3B-Coder-APEX-MTP-GGUF: Quantization
- mradermacher/Qwopus3.6-35B-A3B-Coder-i1-GGUF: Quantization
- pragmaticcs/Qwen-35B-A3B-SignOfFour-Coder: Full fine-tune
- mradermacher/Qwopus3.6-35B-A3B-Coder-GGUF: Quantization
- rcmorano/Jackrong-Qwopus3.6-35B-A3B-Coder-ROCMFPX: Same weights, converted
- OliviaRossi/UltiMerge: Full fine-tune (fewer layers)
- el4/Qwopus3.6-35B-A3B-Coder-OPAL-GGUF: Quantization
- jashepp/Qwopus3.6-35B-A3B-Coder-MXFP4_MOE_Hybrid-Imatrix-GGUF: Quantization
- dgr237/Qwopus3.6-35B-A3B-Coder-NVFP4: Quantization
- nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-1M-qx86-hi-mlx: Quantization
- nightmedia/Qwen3.6-35B-A3B-Fable-Holo3.1-Qwopus-Coder-Text-qx64-hi-mlx: Quantization
- Shiftedx/qwopus3.6-35b-a3b-coder-abliterated-mxfp4-vision-mlx: Quantization
- xero0000/Qwopus3.6-35B-A3B-Coder-vram13-GGUF: Quantization
1 other repos hold byte-for-byte identical weight files.