tensorblock/tiny-llama3-test-GGUF

Quantization vs ariG23498/tiny-llama3-test. tensorblock/tiny-llama3-test-GGUF is a GGUF quantization (Q3_K_M) of the same weights: 3 tensors match exactly and 9 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/3, MLP 0/3, Attention 0/4, lm_head 0/1

On the Hub · Downloads on Model Pulse