mradermacher/Wrench-4B-Qwen3.6-8E-GGUF

Same weights, converted vs stancsz/Wrench-4B-Qwen3.6-8E-Experimental-Preview. Same weights stored in another dtype (BF16 → F16/F32), plus 150 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/101, MLP 0/160, Attention 0/40

On the Hub · Downloads on Model Pulse