techwithsergiu/Qwen3.5-text-0.8B
Same weights, repacked (fewer layers) vs Qwen/Qwen3.5-0.8B. techwithsergiu/Qwen3.5-text-0.8B matches part of Qwen/Qwen3.5-0.8B (335 of its 488 tensors; the rest of Qwen/Qwen3.5-0.8B has no counterpart). On the shared part: Same weights in different files (re-saved, re-sharded or new metadata).
Tensors changed: Attention 0/172, Norms 0/85, Embeddings 0/2, MLP 0/75, other 0/1
2 derivatives checked
- techwithsergiu/Qwen3.5-text-0.8B-GGUF: Same weights, converted
- techwithsergiu/Qwen3.5-text-0.8B-bnb-4bit: Quantization