itlwas/DeepSeek-V2-Lite-Chat-Q4_K_M-GGUF

Quantization vs deepseek-ai/DeepSeek-V2-Lite-Chat. itlwas/DeepSeek-V2-Lite-Chat-Q4_K_M-GGUF is a GGUF quantization (Q4_K_M) 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