gabriellarson/reka-flash-3.1-GGUF

Quantization vs RekaAI/reka-flash-3.1. gabriellarson/reka-flash-3.1-GGUF is a GGUF quantization (Q8_0) of the same weights: 89 tensors match exactly and 310 within quantization error.

Tensors changed: Attention 0/176, Norms 0/89, MLP 0/132, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse