mradermacher/mistral_18B_instruct_v0.1-GGUF

Quantization vs cloudyu/mistral_18B_instruct_v0.1. mradermacher/mistral_18B_instruct_v0.1-GGUF is a GGUF quantization (Q8_0) of the same weights: 162 tensors match exactly and 561 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/161, MLP 0/240, Attention 0/320, lm_head 0/1

On the Hub · Downloads on Model Pulse