Codestral Mamba Architecture

5 posts · May 2024 – Dec 2025

What this trail covers

Mistral AI continues to advance its coding models with Codestral Mamba, a 7B parameter model based on the Mamba architecture. This model offers linear time inference and the ability to model sequences of infinite length, making it efficient for code productivity use cases. It has been trained with advanced code and reasoning capabilities and tested on in-context retrieval up to 256k tokens, positioning it as a strong local code assistant. The model is available for free use, modification, and distribution under Apache 2.0.

All Mistral AI trails

Dec 2025Introducing: Devstral 2 and Mistral Vibe CLI. | Mistral AIIntroduces Devstral 2 (123B) and Devstral Small 2 (24B) coding models, with Devstral 2 achieving 72.2% on SWE-bench Verified and offering a 256K context window. Highlights cost-efficiency and smaller parameter counts compared to competitors. Releases Mistral Vibe CLI, an open-source terminal agent for autonomous code automation, featuring project-aware context, multi-file orchestration, and IDE integration. Details API pricing and deployment recommendations for data center and consumer hardware.
Jul 2025Announcing Codestral 25.08 and the Complete Mistral Coding Stack for Enterprise | Mistral AIThis post announces Codestral 25.08 with specific performance improvements in completion acceptance, code retention, and generation stability. It also introduces the broader Mistral Coding Stack for Enterprise, which integrates Codestral Embed for codebase-scale search, Devstral for agentic workflows, and Mistral Code for IDE integration. Key enterprise-focused features include self-deployment options (cloud, VPC, on-prem), no mandatory telemetry, SSO, audit logging, and usage observability via the Mistral Console. The post highlights how these components work together for a full-stack AI-native software development solution.
Jun 2025Introducing Mistral Code | Mistral AIIntroduces Mistral Code, an enterprise AI coding assistant that bundles Codestral, Codestral Embed, Devstral, and Mistral Medium models with an in-IDE assistant and enterprise tooling. It enhances the Continue project with enterprise-grade features like RBAC, audit logging, and usage analytics. The offering supports local deployment (on-prem, air-gapped), model fine-tuning/post-training on private data, and multi-step coding tasks. It provides a vertically-integrated solution with unified SLAs for enterprise adoption.
May 2025Devstral | Mistral AIIntroduces Devstral, an agentic LLM for software engineering tasks, outperforming open-source models on SWE-Bench Verified. Highlights its ability to tackle real-world software engineering problems by contextualizing code and identifying bugs. Discusses its versatility for local deployment, enterprise use on privacy-sensitive repositories, and integration into agentic coding IDEs. Provides availability details for API and self-deployment, and offers enterprise customization options.
Jul 2024Codestral Mamba | Mistral AIIntroduces Codestral Mamba, a 7B parameter model based on the Mamba architecture, offering linear time inference and the ability to model sequences of infinite length. This model is trained with advanced code and reasoning capabilities and tested for in-context retrieval up to 256k tokens. It is available for free use, modification, and distribution under Apache 2.0, and can be deployed via mistral-inference SDK, TensorRT-LLM, and is expected to be supported in llama.cpp.
Advertisement
May 2024Codestral | Mistral AIThis post introduces Codestral, a new 22B parameter code generation model. It details its training on over 80 programming languages, its fill-in-the-middle capabilities, and its performance benchmarks across Python, SQL, and other languages, highlighting its superiority in RepoBench due to a 32k context window. It also announces the availability of a dedicated `codestral.mistral.ai` API endpoint, its integration with popular developer tools and frameworks, and licensing details.