fluently/FluentlyQwen3-Coder-4B-0909
LoRA-style vs fluently/FluentlyQwen3-4B. 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 36 of 36 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 108/108, Attention 144/144
5 derivatives checked
- mradermacher/FluentlyQwen3-Coder-4B-i1-GGUF: Quantization
- mradermacher/FluentlyQwen3-Coder-4B-0909-i1-GGUF: Quantization
- mradermacher/FluentlyQwen3-Coder-4B-GGUF: LoRA-style
- DevQuasar/fluently.FluentlyQwen3-Coder-4B-0909-GGUF: Same weights, converted
- mradermacher/FluentlyQwen3-Coder-4B-0909-GGUF: Same weights, converted