Open Systems, Blockchain & Business Daily

OSBBD

AI, money and the software behind them.

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
PageURL
Hugging Face model cardhttps://huggingface.co/mistralai/Magistral-Small-2509/raw/main/README.md
Hugging Face weights indexhttps://huggingface.co/mistralai/Magistral-Small-2509/raw/main/model.safetensors.index.json
OSBBD

What are you looking for?

Search by headline, topic or keyword.