Flux.1 [dev]IMAGENewA new SOTA image generation model that is outstanding in prompt following and visual quality.Llama-3.1-405B-BASELLMBF16PopularStill the SOTA base completion model but better because it's BF16.DeepSeek-R1LLMFP8NewThe best open-source reasoner LLM released by DeepSeek.Previous slideNext slideAll Models Text Image VLM Base AudioVLM ModelsQwen2.5-VL-72B-InstructLatest and biggest vision model from the Qwen Team.VLMBF16Qwen2.5-VL-7B-InstructVision model from the Qwen Team.VLMBF16Pixtral-12BVision model from MistralAI.VLMBF16Clear filters