unsloth/Qwen3.5-4B-GGUF
Same weights, converted vs Qwen/Qwen3.5-4B. Same weights stored in another dtype (BF16/F32 → BF16/F32), plus 24 new tensors.
Tensors changed: Embeddings 0/1, MLP 0/96, Norms 0/81, Attention 0/32
4 derivatives checked
- preferedev/Roblox-Coder-v2_gguf: Full fine-tune
- preferedev/Roblox_Coder_gguf: Full fine-tune
- tpgz/qwen3.5vl-4b-Q5-Q4: Full fine-tune
- PavelH-cz/RuxAI-deepseekr1-distill-qwen3.5-4B-GGUF: Partial fine-tune