tensorblock/TinyLlama-1.1B-Chat-v0.4-GGUF
Quantization vs TinyLlama/TinyLlama-1.1B-Chat-v0.4. tensorblock/TinyLlama-1.1B-Chat-v0.4-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 45 tensors match exactly and 156 within quantization error.
Tensors changed: lm_head 0/1, Embeddings 0/1, Norms 0/45, MLP 0/66, Attention 0/88