OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Paper • 2308.13137 • Published • 19
4-bit OmniQuant quantized version of mistralai/Mistral-Small-24B-Instruct-2501 for inference with the Private LLM app.
- Downloads last month
- -
Model tree for numen-tech/Mistral-Small-24B-Instruct-2501-w4a16g128asym
Base model
mistralai/Mistral-Small-24B-Base-2501