TeichAI/Qwen3-1.7B-Gemini-2.5-Flash-Lite-Preview-Distill-GGUF

Same weights, converted vs TeichAI/Qwen3-1.7B-Gemini-2.5-Flash-Lite-Preview-Distill. Same weights stored in another dtype (BF16 → F16/F32).

Tensors changed: Embeddings 0/1, Norms 0/113, MLP 0/84, Attention 0/112

On the Hub · Downloads on Model Pulse