Felladrin/gguf-Lite-Mistral-150M-v2-Instruct

Quantization vs OuteAI/Lite-Mistral-150M-v2-Instruct. Felladrin/gguf-Lite-Mistral-150M-v2-Instruct is a GGUF quantization (IQ2_XXS) of the same weights: 27 tensors match exactly and 84 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/25, MLP 0/36, Attention 0/48

On the Hub · Downloads on Model Pulse