bartowski/lemon07r_VellumMini-0.1-Qwen3-14B-GGUF

Same weights, converted vs lemon07r/VellumMini-0.1-Qwen3-14B. Same weights stored in another dtype (BF16 → BF16/F32).

Tensors changed: MLP 0/120, Attention 0/160, Norms 0/161, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse