LuffyTheFox/Swift-Qwen3.8-27B-Genesis-GGUF
LoRA-style vs ukisai/Swift-Qwen3.8-27b. LuffyTheFox/Swift-Qwen3.8-27B-Genesis-GGUF is a GGUF (F16) of different weights. 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 64 of 64 layers; norms, biases and embeddings are untouched.
Tensors changed: Norms 0/161, MLP 192/192, Attention 64/64, Embeddings 0/1, lm_head 0/1
1 derivatives checked
- jan1k/Swift-Qwen3.8-27B-Genesis-NVFP4-GGUF: Same weights, repacked