mradermacher/A2FM-32B-rl-GGUF

Quantization vs PersonalAILab/A2FM-32B-rl. mradermacher/A2FM-32B-rl-GGUF is a GGUF quantization (Q8_0) of the same weights: 321 tensors match exactly and 450 within quantization error.

Tensors changed: Attention 0/448, Norms 0/129, MLP 0/192, lm_head 0/1, Embeddings 0/1

On the Hub · Downloads on Model Pulse