mradermacher/nyun-c1-llama3-62B-i1-GGUF

Quantization vs nyunai/nyun-c1-llama3-62B. mradermacher/nyun-c1-llama3-62B-i1-GGUF is a GGUF quantization (Q5_K_M) of the same weights: 141 tensors match exactly and 492 within quantization error.

Tensors changed: Embeddings 0/1, Norms 0/141, MLP 0/210, Attention 0/280, lm_head 0/1

On the Hub · Downloads on Model Pulse