This is an FP8 quantized variant of Mistral Small 3.2 24B Instruct using compressed-tensors. It supports image-text-to-text tasks and is optimized for efficient inference with vLLM. The model is suitable for developers seeking high-performance multimodal capabilities with lower memory footprint.
Mistral Small 3.2 24B Instruct 2506 sits in PulseGate's Foundation models & chat category. It focuses on running large multimodal instruction models efficiently on hardware with reduced memory and compute requirements. Mistral Small 3.2 24B Instruct 2506 is an open-source project aimed at developers. The project is open source (Apache-2.0). It runs on the web, the command line, and API.
stelterlab builds and maintains Mistral Small 3.2 24B Instruct 2506, and the product first shipped in 2019. The project is developed in the open on GitHub with 3.6k stars and 163 commits in the last 90 days. PulseGate's similarity index places it among 5 comparable tools. Among its 3 catalogued features are FP8 Quantization, multimodal, and Instruction Following.
Latest indexed changes and source events
stelterlab/Mistral-Small-3.2-24B-Instruct-2506-FP8 verified by the PulseGate indexer
Other apps tracked under the same category.
