Jackrong/Qwopus3.5-9B-Coder
LoRA-style vs Jackrong/Qwopus3.5-9B-v3.5. 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 32 of 32 layers; norms, biases and embeddings are untouched.
Tensors changed: lm_head 0/1, Embeddings 0/5, MLP 96/211, Attention 56/336, other 0/1, Norms 0/221
19 derivatives checked
- mradermacher/Qwopus3.5-9B-Coder-i1-GGUF: Quantization
- noctrex/Qwopus3.5-9B-Coder-MTP: Not comparable yet
- joeblowma/Qwopus3.5-9B-Coder-MTP-GGUF: Quantization
- mradermacher/Qwopus3.5-9B-Coder-GGUF: Same weights, converted
- prithivMLmods/Zenith-9B-CodeCore-Merge: Full fine-tune
- nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Qwythos-qx86-hi-mlx: Quantization
- pragmaticcs/Triumvirate-Qwopus-MiMo-Ornith-9B-Coder: Full fine-tune (fewer layers)
- pragmaticcs/PentaCoder-9B: Full fine-tune (fewer layers)
- paulalesius/Qwopus3.5-9B-Coder-NVFP4-GGUF: Quantization
- prithivMLmods/Vortex-9B-CodeCore-Merge: Full fine-tune
- OliviaRossi/Qwen3.5-9B-C3SM-SDM-Agentic-Coder: Full fine-tune (fewer layers)
- nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable-Polaris-qx86-hi-mlx: Quantization
- tongrow/MLX-Qwopus3.5-9B-Coder-oQ4-fp16-mtp: Quantization
- WineryLabs/Winery-Qwen3.5-9B-Atelier-GGUF: Full fine-tune
- nightmedia/Qwen3.5-9B-TNG-PKD-Qwopus-Coder-Fable-Polaris-mxfp4-mlx: Quantization
- compute1/qwopus3.5-9b-coder-awq-int4: Quantization
- Wiself/Holodeck-Lounge-MTP-GGUF: Full fine-tune
- nbeerbower/Hemlock-Qwopus3.5-9B-Coder: LoRA-style
- Wiself/Holodeck-Lounge-MTP: Full fine-tune