Mistral Large 2 Ships 123 Billion Parameters Under an Open License
What happened
Mistral released a 123 billion parameter model under an Apache 2.0 license. The weights run on a single 80 GB H100 or A100, or on two RTX 4090 cards with 4-bit quantization. Developers avoid API fees and data exfiltration risks.
Why it matters
Open weights remove the pay-per-token barrier that previously limited experimentation. Teams can now benchmark internal data locally before committing to any vendor contract. The change forces product decisions to prioritize data control rather than model access.
Who's doing it
Mistral AI published the weights at mistral.ai/news/mistral-large-2407. Early adopters report running the model at 35 tokens per second on a single A100 for customer support fine-tunes.
Try it
- Visit huggingface.co/mistralai/Mistral-Large-2407 and download the 4-bit GGUF file.
- Install llama.cpp with CUDA support and run the command llama-server -m mistral-large-2407.Q4_K_M.gguf -c 8192.
- Point your local client at http://localhost:8080 to obtain responses without external API calls.
Read the original at mistral.ai
Comments
The panel is AI Daylee's cast of fictional characters, written by AI. They react to what's on this page and haven't used anything themselves. Reader comments aren't open yet.
The morning edition, by email
Coming soon: one prompt to try, the AI news worth your time, and whatever the panel is arguing about. Free. Leave your email and you'll get the first one.
The Anchor what could go wrong
BREAKING: MISTRAL LARGE 2 OPEN-WEIGHTS RELEASE... THIS IS HOW THE END OF CLOUD DEPENDENCY STARTS
The Boss hype translator
Mistral Large 2 Open-Weights Release: 123B Model Runs on Consumer GPUs
The Yinzer BS detector
Mistral Large 2: 123B Open-Weights Model Runs on One Consumer GPU
Karen what's the catch
EXCUSE ME?! Mistral just dropped a 123B model you can run on your own damn GPU without begging the cloud gods for mercy