# \#mamba **URL:** https://www.artofsm.art/tag/mamba/131.md [Latest](https://www.artofsm.art/latest.md) · [Categories](https://www.artofsm.art/categories.md) · [Tags](https://www.artofsm.art/tags.md) --- ## [What are State Space Models? Redefining AI & Machine Learning with Data](https://www.artofsm.art/t/what-are-state-space-models-redefining-ai-machine-learning-with-data/15299)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [15 January 2026 12:20 UTC](https://www.artofsm.art/t/what-are-state-space-models-redefining-ai-machine-learning-with-data/15299 "2026-01-15T12:20:59Z")
State Space Models (SSMs) are a new approach in AI and machine learning that efficiently handle sequential data by using memory-like structures to track and predict evolving information over time, offering … --- ## [Build anything with Local AI Models, here's how](https://www.artofsm.art/t/build-anything-with-local-ai-models-heres-how/14929)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [22 December 2025 20:06 UTC](https://www.artofsm.art/t/build-anything-with-local-ai-models-heres-how/14929 "2025-12-22T20:06:05Z")
The video explains how recent advancements allow users to run powerful AI models locally on their own devices, offering benefits like privacy, customization, and no ongoing costs. It demonstrates using LM S… --- ## [Google’s New Breakthrough Brings AGI Even Closer - Titans and Miras](https://www.artofsm.art/t/google-s-new-breakthrough-brings-agi-even-closer-titans-and-miras/14483)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [5 December 2025 21:35 UTC](https://www.artofsm.art/t/google-s-new-breakthrough-brings-agi-even-closer-titans-and-miras/14483 "2025-12-05T21:35:17Z")
Google’s new AI breakthroughs, Titans and Miras, introduce a novel memory architecture inspired by the human brain, enabling models to maintain genuine long-term memory and understand vast amounts of inform… --- ## [Granite 4.0: Small AI Models, Big Efficiency](https://www.artofsm.art/t/granite-4-0-small-ai-models-big-efficiency/13651)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [30 October 2025 11:24 UTC](https://www.artofsm.art/t/granite-4-0-small-ai-models-big-efficiency/13651 "2025-10-30T11:24:23Z")
The video highlights IBM’s Granite 4.0 series of small, efficient AI language models that combine Transformers with the Mamba 2 state space model to deliver high performance, exceptional memory efficiency, … --- ## [nVidia HYMBA-1.5B: Tiny Agentic Hybrid Models are the NEXT Frontier of Local AI](https://www.artofsm.art/t/nvidia-hymba-1-5b-tiny-agentic-hybrid-models-are-the-next-frontier-of-local-ai/3898)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [22 November 2024 21:39 UTC](https://www.artofsm.art/t/nvidia-hymba-1-5b-tiny-agentic-hybrid-models-are-the-next-frontier-of-local-ai/3898 "2024-11-22T21:39:07Z")
Nvidia’s HYMBA (Hybrid Model for Small Language Models) is a 1.5 billion parameter model designed for local AI, particularly for edge devices, that combines Transformers with state space models to enhance c… --- ## [Zamba 2 is a Hybrid Mamba + Transformers Model (Fully Tested)](https://www.artofsm.art/t/zamba-2-is-a-hybrid-mamba-transformers-model-fully-tested/3391)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [29 October 2024 15:31 UTC](https://www.artofsm.art/t/zamba-2-is-a-hybrid-mamba-transformers-model-fully-tested/3391 "2024-10-29T15:31:40Z")
The video introduces Zamba 2, a new non-Transformers model by Zyer, which claims to outperform leading models in quality and performance, particularly for on-device applications, but the presenter expresses… --- ## [Zamba2-7B: Paving the Way for Small Agentic AI Models](https://www.artofsm.art/t/zamba2-7b-paving-the-way-for-small-agentic-ai-models/2950)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [15 October 2024 20:33 UTC](https://www.artofsm.art/t/zamba2-7b-paving-the-way-for-small-agentic-ai-models/2950 "2024-10-15T20:33:30Z")
The video highlights the advancements of the Zamba 2-7B small language model developed by ZRA, which outperforms larger models like Llama 3 and Mistal 7B in efficiency and performance while being suitable f… --- ## [Were RNNs All We Needed? (Paper Explained)](https://www.artofsm.art/t/were-rnns-all-we-needed-paper-explained/2825)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [12 October 2024 12:15 UTC](https://www.artofsm.art/t/were-rnns-all-we-needed-paper-explained/2825 "2024-10-12T12:15:57Z")
The video reviews the paper “Were RNNs All We Needed?” which argues that simpler RNN models might perform as well as more complex architectures like S4 and Mamba, although it critiques the weak experimental… --- ## [Liquid LFM 40B: The Next Frontier in Transformer AI Architecture](https://www.artofsm.art/t/liquid-lfm-40b-the-next-frontier-in-transformer-ai-architecture/2307)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [2 October 2024 21:45 UTC](https://www.artofsm.art/t/liquid-lfm-40b-the-next-frontier-in-transformer-ai-architecture/2307 "2024-10-02T21:45:59Z")
The video introduces Liquid Foundation Models (LFMs) by Liquid AI, a new architecture designed for efficiency and memory usage in generative AI tasks, featuring models with up to 40 billion parameters and a… --- ## [Jamba Model Is Painful to Use (Mamba-Based Architecture)](https://www.artofsm.art/t/jamba-model-is-painful-to-use-mamba-based-architecture/1719)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [26 August 2024 15:58 UTC](https://www.artofsm.art/t/jamba-model-is-painful-to-use-mamba-based-architecture/1719 "2024-08-26T15:58:02Z")
The video reviews the Jamba 1.5 model, based on the Mamba architecture, highlighting its slow performance and frequent inaccuracies in tasks such as coding and mathematical reasoning. Despite some minor suc… --- ## [Nvidia 🐍 Mamba-2 Hybrid 8B is Incredible!](https://www.artofsm.art/t/nvidia-mamba-2-hybrid-8b-is-incredible/808)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [17 June 2024 23:50 UTC](https://www.artofsm.art/t/nvidia-mamba-2-hybrid-8b-is-incredible/808 "2024-06-17T23:50:03Z")
The video discusses Nvidia’s recent focus on generating large amounts of data to enhance their AI models and surpass benchmarks like Llama 3. It also highlights quieter releases from Nvidia that may have a … --- ## [🐍 Mamba2 8B Hybrid 🚀: NVIDIA Stealth drops their latest Mamba2 Model!](https://www.artofsm.art/t/mamba2-8b-hybrid-nvidia-stealth-drops-their-latest-mamba2-model/807)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [17 June 2024 20:40 UTC](https://www.artofsm.art/t/mamba2-8b-hybrid-nvidia-stealth-drops-their-latest-mamba2-model/807 "2024-06-17T20:40:03Z")
The video discusses Nvidia’s recent release of the Mamba2 Hybrid 8B model, showcasing its performance advancements and scalability in comparison to Transformer-based models. It highlights the significance o… --- ## [MAMBA from Scratch: Neural Nets Better and Faster than Transformers](https://www.artofsm.art/t/mamba-from-scratch-neural-nets-better-and-faster-than-transformers/350)
**Author:** [@merefield](https://www.artofsm.art/u/merefield)\ **Replies:** 1\ **Last updated:** [1 May 2024 05:43 UTC](https://www.artofsm.art/t/mamba-from-scratch-neural-nets-better-and-faster-than-transformers/350 "2024-05-01T05:43:42Z")
The video introduces Mamba, a new neural network architecture that claims to outperform transformers in language modeling due to its computational efficiency and innovative handling of memory transfer. It a… --- ## [The Largest Mamba LLM Experiment Just Dropped](https://www.artofsm.art/t/the-largest-mamba-llm-experiment-just-dropped/1389)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [17 April 2024 20:13 UTC](https://www.artofsm.art/t/the-largest-mamba-llm-experiment-just-dropped/1389 "2024-04-17T20:13:54Z")
The video discusses the launch of the Jumba model, a hybrid of the Mamba and Transformer architectures, which significantly improves long-context processing and efficiency, boasting 52 billion parameters wh… --- ## [Mamba Might Just Make LLMs 1000x Cheaper](https://www.artofsm.art/t/mamba-might-just-make-llms-1000x-cheaper/1387)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [24 February 2024 16:24 UTC](https://www.artofsm.art/t/mamba-might-just-make-llms-1000x-cheaper/1387 "2024-02-24T16:24:12Z")
The video introduces Mamba, a new architecture for AI chatbots that promises to be 1,000 times cheaper than traditional Transformers by utilizing a linear scaling computation method and an innovative gated … --- ## [Mamba: Linear-Time Sequence Modeling with Selective State Spaces (Paper Explained)](https://www.artofsm.art/t/mamba-linear-time-sequence-modeling-with-selective-state-spaces-paper-explained/1388)
**Author:** [@artesia](https://www.artofsm.art/u/artesia)\ **Replies:** 1\ **Last updated:** [24 December 2023 15:49 UTC](https://www.artofsm.art/t/mamba-linear-time-sequence-modeling-with-selective-state-spaces-paper-explained/1388 "2023-12-24T15:49:29Z")
The video discusses the Mamba architecture for sequence modeling, which offers a linear-time approach with Selective State Spaces, allowing it to efficiently handle long sequences while competing with tradi…