Magistral Small 1.2
Magistral Small 1.2 is an open-weight language model from Mistral AI, released in September 2025. It is a dense model with 24B parameters. Mistral AI lists a context window of 128K tokens. The model accepts text and image input.
- Developer
- Mistral AI
- Released
- September 2025
- Total parameters
- 24B
- Architecture
- Dense
- Context window
- 128K
- Input
- Text, image
- License
- Apache 2.0
- Commercial use
- Yes
- Official weights, GB
- 48 GB
- Hugging Face repository
- huggingface.co
- Checked on
The weights are released under Apache 2.0, which allows commercial use.
The official weights on Hugging Face take about 48.0 GB in BF16. Running the model needs at least that much memory across GPUs and system RAM, plus room for the context cache; quantized versions need less.
- Total parameters, billions
- 24B
- Context window, tokens
- 128K
- License type
- Apache 2.0
- License conditions
- Apache 2.0, with no user or revenue limits.
- Weights precision
- BF16
- Official quantized or alternative versions
- mistralai/Magistral-Small-2509-GGUF
- License text
- apache.org
- Sources
Page URL Hugging Face model card https://huggingface.co/mistralai/Magistral-Small-2509/raw/main/README.md Hugging Face weights index https://huggingface.co/mistralai/Magistral-Small-2509/raw/main/model.safetensors.index.json