mradermacher/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts-GGUF

Same weights, converted vs AmanPriyanshu/gpt-oss-6.0b-specialized-all-pruned-moe-only-7-experts. Same weights stored in another dtype (BF16 → F16/F32), plus 168 new tensors.

Tensors changed: Embeddings 0/1, Norms 0/49, MLP 0/48, Attention 0/192, lm_head 0/1

On the Hub · Downloads on Model Pulse