llmfan46/gpt-oss-120b-heretic-v2-GGUF

Same weights, converted vs llmfan46/gpt-oss-120b-heretic-v2. Same weights stored in another dtype (U8/BF16 → MXFP4/BF16), plus 252 new tensors.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/73, MLP 0/72, Attention 0/288

On the Hub · Downloads on Model Pulse