RedHatAI/SmolLM-135M-Instruct-quantized.w8a16

Quantization vs HuggingFaceTB/SmolLM-135M-Instruct. RedHatAI/SmolLM-135M-Instruct-quantized.w8a16 is a quantized version of the other (BF16/I32).

On the Hub · Downloads on Model Pulse