lilmeaty/SmolLM2-135M-Instruct-GPTQ

Quantization vs HuggingFaceTB/SmolLM2-135M. lilmeaty/SmolLM2-135M-Instruct-GPTQ is a quantized version of the other (F16/I32).

1 other repos hold byte-for-byte identical weight files.

On the Hub · Downloads on Model Pulse