devon7y/WikiQwen-35B-A3B
LoRA-style (fewer layers) vs Qwen/Qwen3.6-35B-A3B. devon7y/WikiQwen-35B-A3B matches part of Qwen/Qwen3.6-35B-A3B (693 of its 1045 tensors; the rest of Qwen/Qwen3.6-35B-A3B has no counterpart). On the shared part: 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 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Attention 40/280, MLP 120/280, Norms 0/131, lm_head 0/1
3 derivatives checked
- mradermacher/WikiQwen-35B-A3B-i1-GGUF: Quantization
- mradermacher/WikiQwen-35B-A3B-GGUF: Quantization
- ramgpt/WikiQwen-35B-A3B-GGUF: Quantization