lemuralabs/MiniMax-M2-Pruned-55

Quantization vs MiniMaxAI/MiniMax-M2. MiniMaxAI/MiniMax-M2 is a quantized version of the other (F8_E4M3/BF16).

2 derivatives checked

• mradermacher/MiniMax-M2-THRIFT-55-i1-GGUF: Quantization
• mradermacher/MiniMax-M2-THRIFT-55-GGUF: Quantization

On the Hub · Downloads on Model Pulse