tiyuvta/DictaLM-3.0-24B-NVFP4
Quantization vs dicta-il/DictaLM-3.0-24B-Thinking. tiyuvta/DictaLM-3.0-24B-NVFP4 is a quantized version of the other (U8/BF16).
Quantization vs dicta-il/DictaLM-3.0-24B-Thinking. tiyuvta/DictaLM-3.0-24B-NVFP4 is a quantized version of the other (U8/BF16).