State-of-the-art open code model with deep reasoning, 256k context, and unmatched efficiency.
State-of-the-art open code model with deep reasoning, 256k context, and unmatched efficiency.
Devstral 2 123B Instruct 2512 is an agentic large language model designed for software engineering tasks. The model excels at using tools to explore codebases, editing multiple files, and powering software engineering agents, achieving remarkable performance on SWE-bench benchmarks.
This model is ready for commercial/non-commercial use.
This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA Devstral 2 123B Instruct 2512 FP8 Model Card
GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service. Use of this model is governed by the Modified MIT license.
Global
Use Case: AI code assistants, agentic coding, and software engineering tasks. Designed for developers and organizations leveraging advanced AI capabilities for complex tool integration and deep codebase understanding in coding environments.
Build.NVIDIA.com: 12/2025 via link
Huggingface: 12/2025 via link
References:
Architecture Type: Transformer
Network Architecture: Mixture-of-Experts with rope-scaling
Total Parameters: 123B
Input Types: Text
Input Formats: String
Input Parameters: One Dimensional (1D)
Other Input Properties: Text prompts for code generation and agentic coding tasks; supports system prompts for specialized behavior.
Output Types: Text
Output Format: String
Output Parameters: One Dimensional (1D)
Other Output Properties: Generated code, tool calls, and natural language responses for software engineering tasks.
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.
Runtime Engines:
Supported Hardware:
Operating Systems: Linux
The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.
v1.0 (December 2025) - FP8 quantized variant
Data Modality: Text
Training Data Collection: Undisclosed
Training Labeling: Undisclosed
Training Properties: Undisclosed
Testing Data Collection: Undisclosed
Testing Labeling: Undisclosed
Testing Properties: Undisclosed
Evaluation Benchmark Score: 72.2% on SWE-Bench Verified; 61.3% on SWE-Bench Multilingual; 40.5% on Terminal Bench
Evaluation Data Collection: Automated
Evaluation Labeling: Human
Evaluation Properties: SWE-Bench Verified, SWE-Bench Multilingual, and Terminal Bench are standard benchmarks for evaluating software engineering capabilities in AI models.
Acceleration Engine: vLLM with mistral-common tokenizer
Test Hardware: 8× NVIDIA GPU with tensor parallelism (FP8 precision)
Devstral 2 can be deployed using:
For optimal performance, deploy with:
--tool-call-parser mistral --enable-auto-tool-choiceNVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns here.