ghecko78/Qwen3-Coder-Next-Heretic-GGUF

Quantization vs trohrbaugh/Qwen3-Coder-Next-heretic. ghecko78/Qwen3-Coder-Next-Heretic-GGUF is a GGUF quantization (Q8_0) of the same weights: 169 tensors match exactly and 194 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/121, MLP 0/192, Attention 0/48

On the Hub · Downloads on Model Pulse