QriticalBeta
Open Model Catalogue
Mistral AI
Mistral AI
CodingText generation

Devstral 2 123B

mistralai/Devstral-2-123B-Instruct-2512

Agentic coding flagship — 2 × 80 GB

Deploy Devstral 2 123B nowView on HuggingFace
Parameters
123B · FP8
Min VRAM
≈ 150 GB
Hardware
2 × 80 GB GPU
OpenAI-compatible API with a per-workload key — drop-in for existing SDKs.
Dedicated GPUs — your model, your instance, no shared queues.
Billed by the second with auto-shutdown — never pay for idle time you didn't plan.