Vikhrmodels/Vistral-24B-Instruct
TEXT GENERATIONConcurrency Cost:2Model Size:24BQuant:FP8Ctx Length:32kPublished:Sep 28, 2025License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Vikhrmodels/Vistral-24B-Instruct is a 24 billion parameter unimodal large language model developed by VikhrModels, based on Mistral-Small-3.2-24B-Instruct-2506. Optimized primarily for Russian and English, this model removes the visual encoder and multimodal capabilities of its base. It excels in instruction following for both languages, demonstrating strong performance on Russian-language benchmarks.

Loading preview...