Alexs28/Qwen3.5-0.8B-heretic-250-v1-GGUF

Quantization vs coder3101/Qwen3.5-0.8B-heretic. Alexs28/Qwen3.5-0.8B-heretic-250-v1-GGUF is a GGUF quantization (Q8_0/F16) of the same weights: 99 tensors match exactly and 59 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/61, MLP 0/72, Attention 0/24

On the Hub · Downloads on Model Pulse