cygnal/Qwen3.8-27B-heretic-ara-Q4_K_M-MTP-GGUF

Same weights, converted vs trohrbaugh/Qwen3.8-27B-heretic-ara. Same weights stored in another dtype (BF16 → T101/Q8_0), plus 63 new tensors.

Tensors changed: Norms 0/161

On the Hub · Downloads on Model Pulse