# Mamba-Codestral-7B-v0.1 [Canonical model page](https://headlessthrones.com/models/mistral-ai-mamba-codestral-7b-v0-1) · [Model library](https://headlessthrones.com/models) Public catalog reference from Headless Thrones. Exact catalog ID: `mistral-ai-mamba-codestral-7b-v0-1`. Catalog source-check date: 2026-10-23. This brief contains the public catalog answers and any catalog guide, not private drafts, historical editorial revisions or independently measured rankings. The canonical HTML page may also display separately published editorial. Current catalog answers ## What to know about Mamba-Codestral-7B-v0.1 AI-compiled from linked model documentation. This is a catalog reference, not an independent performance review. Catalog checked October 23, 2026. [Exact model](https://headlessthrones.com/models/mistral-ai-mamba-codestral-7b-v0-1#model-answer-identity) · [Access](https://headlessthrones.com/models/mistral-ai-mamba-codestral-7b-v0-1#model-answer-access) · [Token limits](https://headlessthrones.com/models/mistral-ai-mamba-codestral-7b-v0-1#model-answer-context) · [Dates & knowledge](https://headlessthrones.com/models/mistral-ai-mamba-codestral-7b-v0-1#model-answer-dates) · [License](https://headlessthrones.com/models/mistral-ai-mamba-codestral-7b-v0-1#model-answer-license) · [Model details](https://headlessthrones.com/models/mistral-ai-mamba-codestral-7b-v0-1#model-answer-research) · [Weight details](https://headlessthrones.com/models/mistral-ai-mamba-codestral-7b-v0-1#model-answer-repository) ### Which Mamba-Codestral-7B-v0.1 does this page describe? Mamba-Codestral-7B-v0.1 is a model record from **Mistral AI** in the Codestral family. [Source](https://huggingface.co/mistralai/Mamba-Codestral-7B-v0.1) The recorded model identifier or checkpoint is `0.1`. Use that exact identifier when checking documentation or a provider listing. [Source](https://docs.mistral.ai/models/codestral-mamba-7b-0-1) ### How can you access Mamba-Codestral-7B-v0.1? The catalog records the historical **API and Open weights** access route for Mamba-Codestral-7B-v0.1. [Source](https://docs.mistral.ai/models/codestral-mamba-7b-0-1) As of the catalog check, this version was marked retired. [Source](https://docs.mistral.ai/models/codestral-mamba-7b-0-1) Check the linked lifecycle information before starting a new integration. For a new integration, use the publisher’s replacement guidance and check its current account, region and endpoint requirements. Historical API access does not mean the retired endpoint can still be called. Open weights means the model weights are distributed for use under their stated terms. It does not establish a hosted API, an open-source license, or a hardware requirement. This record documents API access separately. ### What are Mamba-Codestral-7B-v0.1's context and output limits? The documented **context window is 256,000 tokens**. [Source](https://docs.mistral.ai/models/codestral-mamba-7b-0-1) A separate maximum-output value is not established in this record. The context or input figure should not be used as an output allowance. Context, input and output limits describe different constraints. Do not add the figures together to infer a larger window. Check the endpoint's accounting for conversation history, system instructions, tools, media and generated tokens; a documented maximum is not a guarantee of answer quality or a measured usable capacity. ### What dates are documented for Mamba-Codestral-7B-v0.1? **Release date: July 16, 2024.** [Source](https://docs.mistral.ai/models/codestral-mamba-7b-0-1) This is a release milestone, not a knowledge or training cutoff. The source labels this “Release date on Mistral model specification.” Neither a knowledge cutoff nor a training-data cutoff is established here. A release date, repository upload or filename cannot supply those missing dates. ### What license is recorded for Mamba-Codestral-7B-v0.1? The recorded license label is **Apache 2.0**. [Source](https://docs.mistral.ai/models/codestral-mamba-7b-0-1) Read the linked license and associated use terms for this exact version before redistribution, commercial deployment or fine-tuning. A label alone does not establish every permission, restriction or obligation, and it does not determine the terms of a separate hosted service. ### What distinguishes Mamba-Codestral-7B-v0.1? These details come from the linked publisher material for this model. Reported capabilities and training descriptions are publisher statements, not independent test results. **Architecture and specialization**: Code-focused model using the Mamba2 architecture. [Source](https://huggingface.co/mistralai/Mamba-Codestral-7B-v0.1/resolve/4f086c08c1e0f07bdc50ca25125dbbf7475d21da/README.md) **Nominal parameters and deployment**: The release reports 7,285,403,648 parameters and an instructed checkpoint, with deployment through mistral-inference or TensorRT-LLM. [Source](https://mistral.ai/news/codestral-mamba/) **Tested retrieval range**: Mistral reports in-context retrieval tests up to 256k tokens. This is a test result, not a documented maximum context limit. [Source](https://mistral.ai/news/codestral-mamba/) ### What is documented about the Mamba-Codestral-7B-v0.1 checkpoint? This evidence refers to `mistralai/Mamba-Codestral-7B-v0.1` at recorded revision `4f086c08c1e0f07bdc50ca25125dbbf7475d21da`, checked October 23, 2026. [Repository metadata](https://huggingface.co/api/models/mistralai/Mamba-Codestral-7B-v0.1) Safetensors metadata records **7,285,403,648 stored parameters**. This is a stored-weight count, not necessarily the number activated per token, a download size or a GPU-memory requirement. [Repository metadata](https://huggingface.co/api/models/mistralai/Mamba-Codestral-7B-v0.1) Listed library: `vllm`. Check that library's version and model support before loading the weights. [Repository metadata](https://huggingface.co/api/models/mistralai/Mamba-Codestral-7B-v0.1) Repository access gate: `false`. This records the repository's gate setting when checked; licensing and use terms still apply. [Repository metadata](https://huggingface.co/api/models/mistralai/Mamba-Codestral-7B-v0.1) Read the retrieved model card for setup and qualifications. [Model card](https://huggingface.co/mistralai/Mamba-Codestral-7B-v0.1/resolve/4f086c08c1e0f07bdc50ca25125dbbf7475d21da/README.md) **Catalog qualifications:** Official publisher model repository; listed status confirms a catalog entry, not a verified hosted API service. Lifecycle status refers to the Mistral API; publicly listed weights may remain usable under their license. Mistral context shorthand 256k is represented in nominal decimal tokens. [Source 1](https://huggingface.co/api/models/mistralai/Mamba-Codestral-7B-v0.1) · [Source 2](https://huggingface.co/mistralai/Mamba-Codestral-7B-v0.1/resolve/4f086c08c1e0f07bdc50ca25125dbbf7475d21da/README.md) **Evidence still missing here:** complete input/output pricing, knowledge and training-data cutoffs, and tested hardware requirements. Missing documentation is not evidence that a feature is unavailable. Headless Thrones has not independently benchmarked this model for this reference. Evaluate it on representative work before choosing it; these facts do not rank its accuracy, reliability, speed or suitability against another model. Keep the exact version in view ## Other Codestral models from Mistral AI. These are separate records in the same publisher family. A shared family name does not establish equal capabilities or interchangeable licenses. ### [Codestral](https://headlessthrones.com/models/mistral-ai-codestral-25-08) API · 128,000 context tokens ### [Codestral](https://headlessthrones.com/models/mistral-ai-codestral-25-01) API · 128,000 context tokens ### [Codestral-22B-v0.1](https://headlessthrones.com/models/mistral-ai-codestral-22b-v0-1) API · Open weights · 32,000 context tokens