mradermacher/Qwen3-8B-PragReST-GGUF

Same weights, converted vs minchaoh2002/Qwen3-8B-PragReST. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: MLP 0/108, Norms 0/145, Attention 0/144, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse