10 models across 2 families · Latest: Mamba 2 2.7B (2023-12)
Advancing sequence models beyond traditional methods
State Spaces's portfolio covers 10 active models across 2 non-obsolete families, with task labels spanning general LLM work. Open a model detail page to compare provider routes and sourced benchmarks.
Portfolio context: 0 decision-task tags, 10 active tracked models, latest research stamp 2026-05-22.
Use this portfolio page for
- Teams evaluating general LLM work across this lab's releases
- Readers comparing families before locking a flagship SKU
- 10 tracked SKUs for migration and pricing follow-ups
Do not stop here for
- Choosing a hosting provider without opening a model page for price ladders
Active models
10
Non-deprecated SKUs linked to this researcher
Active families
2
Non-obsolete families in coverage
Open catalog
0 OSS
0 open-weight (text match)
Decision task tags
0
Need benchmarks or capability flags
Latest dated release
2023-12-08
Mamba 2 2.7B
Freshness
2026-05-22
Researched 13d ago
Release cadence
Showing 5 recent dated ships (full timeline below). Latest spotlight: Mamba 2 2.7B (2023-12-08).
Where this lab wins
Task positioning unavailable until capability tags or benchmarks populate for active SKUs.
Flagship quality / price signal
Anchor SKU: Mamba 2.8B (best sourced coding Q/$ in this portfolio).
Quality / dollar unavailable for this anchor — missing benchmark coverage and/or output token price on the cheapest ladder route (open the model detail after pricing lands).
State Spaces is an AI research organization founded in N/A. Advancing sequence models beyond traditional methods. State Spaces ships 2 model families totaling 10 models, with the most recent release Mamba 2 2.7B in 2023-12. Notable families include Mamba 2 and Mamba. Use it as a stable reference for lab background, release coverage, and follow-up model pages as they are added. View official API endpoints, benchmark performance, and coding/agent fit for every State Spaces model.
About
State Space Models (SSMs) offer an intriguing alternative to the ubiquitous Transformer architecture in generative AI and large language models (LLMs). Their roots in control theory and signal processing lend a unique perspective to deep learning, particularly for modeling sequences. Initially conceptualized to manage exceptionally lengthy sequences, SSMs were revitalized by the pioneering efforts of Voelker, Kajic, and Eliasmith in 2019. Their work drew from neuroscience, showcasing the potential of SSMs to efficiently synthesize temporal information. This laid the groundwork for subsequent innovations in SSM-based architectures. Albert Gu’s contribution was transformative, particularly in the development of Structured State Space Sequence Models (S4). By ingeniously leveraging the framework of the continuous-time linear time-invariant system, Gu introduced a paradigm shift in how sequence modeling can be approached. The model's foundation relies on two integral equations that manage the evolution of hidden states and their interaction with inputs and outputs. These equations are enhanced by parameterizable matrices, facilitating high-performance levels and computational efficiency. Moreover, Gu's S4 model achieved benchmark-breaking results, particularly excelling in handling long sequences, outstripping the capabilities of conventional Transformers. A significant advantage of the SSM framework is its multifaceted representation, enabling models to be viewed in continuous, recurrent, and convolutional forms. Each view offers distinct advantages across different tasks and data types—continuous views excel with audio data, while recurrent and convolutional views provide computational efficiencies for training and non-linear inference processes. This versatility allows researchers to tailor models precisely to task demands. Additionally, breakthroughs like FlashAttention have significantly optimized the speed and memory efficiency of attention mechanisms, reducing the computational burdens commonly associated with Transformers. Continuing the advancement of SSMs, subsequent research has resulted in the simplification and evolution of the model architecture with creations like the diagonal SSMs. Variants such as S4D maintain the high performance of their predecessors while offering a more streamlined approach to model design. Among these, specialized architectures like Mamba exemplify the potential of SSMs in the context of generative AI. Through its innovative selective scan algorithm, Mamba enhances the efficiency with which relevant information is filtered from lengthy sequences, supporting scalable operation for large language tasks. The FalconMamba model has notably demonstrated these capabilities, scoring high across natural language processing benchmarks, and proving particularly beneficial for enterprise-level applications requiring robust long sequence processing. Conclusively, SSMs present a promising and adaptive framework for sequence modeling, surpassing some inherent limitations of Transformer-based models. The strategic mix of computational efficacy, adaptive multiple view representations, and the development of resource-efficient algorithms have positioned SSMs as a formidable contender in advancing generative AI and LLMs. Emerging research suggests a continuously evolving landscape, with further promising improvements on the horizon.
Featured models
| Model | Released | Context | Input price ($/1M) | Output price ($/1M) | License |
|---|---|---|---|---|---|
| Mamba 2 2.7B | 2023-12-08 | 2k | - | - | Unknown |
| Mamba 2 1.3B | 2023-12-08 | 2k | - | - | Unknown |
| Mamba 2 780M | 2023-12-08 | 2k | - | - | Proprietary |
Model families
Recent releases
- Mamba 2 2.7B- 2023-12-08
- Mamba 2 1.3B- 2023-12-08
- Mamba 2 780M- 2023-12-08
- Mamba 2 370M- 2023-12-08
- Mamba 2 130M- 2023-12-08
FAQ
Who founded State Spaces and when?
State Spaces was founded in N/A and is associated with N/A.
What models has State Spaces released?
State Spaces ships 10 models across 2 families: Mamba 2 and Mamba.
Is State Spaces's technology open source?
State Spaces's tracked models are primarily proprietary, with some license details still being verified.
Where is State Spaces headquartered?
State Spaces is headquartered in N/A.
What is State Spaces known for?
Advancing sequence models beyond traditional methods. Its most prominent tracked family is Mamba 2.
How can I access State Spaces's models?
State Spaces's models are available via Replicate API.
Explore related pages
Last reviewed: 2026-05-22. Data sourced from public lab announcements and provider documentation.