mradermacher/qwen3.8-9b-hermes-fc-tooluse-GGUF

Same weights, converted vs JamieBradfield/qwen3.8-9b-hermes-fc-tooluse. Same weights stored in another dtype (BF16 → F16/F32), plus 39 new tensors.

Tensors changed: MLP 0/96, Attention 0/32, Norms 0/81, Embeddings 0/1, lm_head 0/1

On the Hub · Downloads on Model Pulse