Back to CalculatorView API DocsDeploy Now
Magistral Medium
Enterprise-tier version of Magistral reasoning family. More capable than Magistral Small for complex multi-step tasks in math, law, finance, and code. Available via Mistral API and Le Chat; not open-weight.
Specifications
SourceArchitectureTEXT
Parameters-
Familymagistral
VRAM (Q4)API
API-only reasoning model. Mistral AI has not disclosed the parameter count for the Magistral Medium series. Designed for advanced chain-of-thought, math and multilingual reasoning tasks.
mistralreasoningmultilingualmathenterprisechain-of-thoughtapi-only
Build your Local Rig
Ready to run locally? Shop top-tier GPUs on Amazon for the best performance.
Instant Cloud GPUs
Running out of VRAM? Rent a high-end H100 or RTX 4090 on RunPod and deploy in seconds.
Share this Model
Send these specs directly to your community.
Similar Models
Magistral Small
24BMistral AI's first open-weight reasoning model — 24B parameters under Apache 2.0. Chain-of-thought reasoning in 20+ languages, 70.7% on AIME2024. Fits on a single RTX 4090 or 32GB MacBook.
Llama 3.1 8B
8.03BBest small model for most tasks
Qwen 2.5 72B
72.7BTop-tier reasoning and coding