mradermacher/DeepSeek-V2-Lite-Chat-i1-GGUF

Quantization vs deepseek-ai/DeepSeek-V2-Lite-Chat. mradermacher/DeepSeek-V2-Lite-Chat-i1-GGUF is a GGUF quantization (Q6_K) of the same weights: 108 tensors match exactly and 191 within quantization error.

Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/82, MLP 0/107, Attention 0/108

On the Hub · Downloads on Model Pulse