DevQuasar/ValiantLabs.Qwen3-4B-Esper3-GGUF
Same weights, converted vs ValiantLabs/Qwen3-4B-Esper3. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144
Same weights, converted vs ValiantLabs/Qwen3-4B-Esper3. Same weights stored in another dtype (F32 → F16/F32).
Tensors changed: Embeddings 0/1, Norms 0/145, MLP 0/108, Attention 0/144