AlexWortega/SIQ-1-35B
LoRA-style (fewer layers) vs Qwen/Qwen3.6-35B-A3B. AlexWortega/SIQ-1-35B 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, in_proj_qkv, in_proj_z, k_proj, o_proj, out_proj, q_proj, shared_expert_gate, up_proj, v_proj changed, in 40 of 40 layers; norms, biases and embeddings are untouched.
Tensors changed: Embeddings 0/1, Attention 130/280, MLP 160/280, Norms 0/131, lm_head 0/1
4 derivatives checked
- el4/SIQ-1-35B-OPAL-GGUF: Quantization
- el4/SIQ-1-35B-APEX-GGUF: Quantization
- el4/SIQ-1-35B-ONYX-GGUF: Quantization
- Frosty40/SIQ-1-35B-B70-Turbo-GGUF: Quantization