diljitpr/Qwen3.5-397B-A17B-Q4_K_M-slices
Quantization (fewer layers) vs Qwen/Qwen3.5-397B-A17B. diljitpr/Qwen3.5-397B-A17B-Q4_K_M-slices matches part of Qwen/Qwen3.5-397B-A17B (1 of its 2924 tensors; the rest of Qwen/Qwen3.5-397B-A17B has no counterpart). On the shared part: diljitpr/Qwen3.5-397B-A17B-Q4_K_M-slices is a GGUF quantization (Q8_0) of the same weights: 0 tensors match exactly and 1 within quantization error.
Tensors changed: Embeddings 0/1