# model app **URL:** https://discuss.88.io/c/own-ai/own-interface/desktop-model/313.md?page=1 [Latest](https://discuss.88.io/latest.md) · [Categories](https://discuss.88.io/categories.md) · [Tags](https://discuss.88.io/tags.md) **Page:** 2 --- ## [AI Browser](https://discuss.88.io/t/ai-browser/1773)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [July 13, 2025, 12:03pm UTC](https://discuss.88.io/t/ai-browser/1773 "2025-07-13T12:03:10Z")
GitHub - nanobrowser/nanobrowser: Open-Source Chrome extension for AI-powered web automation. Run multi-agent workflows using your own LLM API key. Alternative to OpenAI Operator. https://www.browseros.com/ --- ## [AI Search](https://discuss.88.io/t/ai-search/1625)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [October 22, 2024, 3:22am UTC](https://discuss.88.io/t/ai-search/1625 "2024-10-22T03:22:12Z")
Recent: GitHub - ItzCrazyKns/Vane: Vane is an AI-powered answering engine. · GitHub GitHub - zaidmukaddam/scira: Scira (Formerly MiniPerplx) is a minimalistic AI-powered search engine that helps you find information on the internet and cites it too. Powered by Vercel AI SDK! · GitHub GitHub - miur… --- ## [Text to Speech](https://discuss.88.io/t/text-to-speech/382)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 4\ **Last updated:** [August 4, 2025, 9:29pm UTC](https://discuss.88.io/t/text-to-speech/382 "2025-08-04T21:29:06Z")
TTS 1. Kokoro 2. Zonos Supports mandarin (cmn) and cantonese (yue) 3. Reviews Increasing number of high quality neural network based TTS are now available: source: AIPrintify Notes: Spark-TTS license changed to non-commercial Language Code A lot of TTS use the language code based o… --- ## [Optical Character Recognition](https://discuss.88.io/t/optical-character-recognition/515)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 1\ **Last updated:** [March 17, 2025, 5:55am UTC](https://discuss.88.io/t/optical-character-recognition/515 "2025-03-17T05:55:14Z")
Optical Character Recognition (OCR) is used extensively for collecting data into your Private Cyberspace. Machine Learning (ML) has made OCR more accurate than ever before, your Private Cyberspace has made ML more secure than ever before. Unlike other Artificial Intelligence (AI) systems, we do NOT… --- ## [Large Language Model](https://discuss.88.io/t/large-language-model/1673)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 1\ **Last updated:** [June 7, 2025, 4:04am UTC](https://discuss.88.io/t/large-language-model/1673 "2025-06-07T04:04:03Z")
AI Everywhere Having standardised AI focused disposable node enables rapid deployment and maintenance of AI infrastructure in the community. --- ## [Devstral](https://discuss.88.io/t/devstral/1746)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [May 25, 2025, 7:43am UTC](https://discuss.88.io/t/devstral/1746 "2025-05-25T07:43:16Z")
Small Coding The Devstral model's small size and focus fits well into Entity Agent's many small models design. https://mistral.ai/news/devstral Benchmarks https://medium.com/@aitechtoolbox48/the-david-vs-goliath-of-ai-how-mistrals-tiny-devstral-is-reshaping-software-development-baca6a464c33 Open… --- ## [SwarmUI](https://discuss.88.io/t/swarmui/1726)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 2\ **Last updated:** [March 8, 2025, 11:50pm UTC](https://discuss.88.io/t/swarmui/1726 "2025-03-08T23:50:59Z")
Interfaces SwarmUI This is recommended. https://www.patreon.com/posts/106135985 Demo https://image.aunsw.88.io Tutorial Beginner’s Guide — Generate Videos With SwarmUI - DEV Community https://www.youtube.com/watch?v=XWzZ2wnzNuQ --- ## [Stable Diffusion](https://discuss.88.io/t/stable-diffusion/1745)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [May 22, 2025, 2:40am UTC](https://discuss.88.io/t/stable-diffusion/1745 "2025-05-22T02:40:52Z")
Stable Diffusion Current Default The stable-diffusion-3.5-medium model is the current default for image servers. stabilityai/stable-diffusion-3.5-medium · Hugging Face References Introducing Stable Diffusion 3.5 — Stability AI SD3.5 | MonAI --- ## [Web Scrapping](https://discuss.88.io/t/web-scrapping/1674)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 3\ **Last updated:** [May 21, 2025, 6:51pm UTC](https://discuss.88.io/t/web-scrapping/1674 "2025-05-21T18:51:46Z")
Remember Your Web Web scrappers are ideal for remembering the web sites you have visited, Browsertrix • Webrecorder --- ## [Whisper-WebUI](https://discuss.88.io/t/whisper-webui/1743)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 1\ **Last updated:** [May 8, 2025, 4:31am UTC](https://discuss.88.io/t/whisper-webui/1743 "2025-05-08T04:31:25Z")
Interface to Whisper Models File, Youtube, Mic large-v3-turbo T2T Translation nllb-200-3.3B BGM Separation UVR-MDX-NET-Inst\_HQ\_4 REST API Whisper-WebUI/backend at master · jhj0517/Whisper-WebUI · GitHub --- ## [Model Set](https://discuss.88.io/t/model-set/1742)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [May 7, 2025, 7:34am UTC](https://discuss.88.io/t/model-set/1742 "2025-05-07T07:34:47Z")
2025 Team Compute Model Set provides a recommended set up for entities developing new AI deployments. 16GB VRAM As of early 2025, the best VRAM size / dollar is from Nvidia 4060 Ti 16GB (with Compute Capability 8.9), we will be using that as reference in creation of Model Sets., but any device with… --- ## [Machine Translation Plus](https://discuss.88.io/t/machine-translation-plus/838)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 3\ **Last updated:** [May 7, 2025, 11:41am UTC](https://discuss.88.io/t/machine-translation-plus/838 "2025-05-07T11:41:25Z")
Currently supported machine translation engines: 1. Dedicated Translation Model NLLB NLLB Serve uses Facebook NLLB GitHub - thammegowda/nllb-serve: Meta's "No Language Left Behind" models served as web app and REST API 2. Large Language Model --- ## [Whisper](https://discuss.88.io/t/whisper/1649)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 2\ **Last updated:** [May 6, 2025, 11:07pm UTC](https://discuss.88.io/t/whisper/1649 "2025-05-06T23:07:28Z")
OpenAI Whisper OpenAI Whisper is one of the best open sourced speech models https://openai.com/index/whisper/ GitHub - openai/whisper: Robust Speech Recognition via Large-Scale Weak Supervision Langauges Whisper supports many languages, including Cantonese: Note it can be used for translation … --- ## [Distributed Language Model](https://discuss.88.io/t/distributed-language-model/1741)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 1\ **Last updated:** [May 5, 2025, 6:19am UTC](https://discuss.88.io/t/distributed-language-model/1741 "2025-05-05T06:19:32Z")
There are many ways of creating LLM clusters VLLM https://docs.vllm.ai/en/latest/serving/distributed\_serving.html Special ClGPUStack GPUStack 0.2: Heterogeneous Distributed Inference – GPUStack.ai While the above can all be used in Disposable Node, we prefer clustering at a higher level: … --- ## [AI Frameworks](https://discuss.88.io/t/ai-frameworks/1739)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [April 30, 2025, 6:01am UTC](https://discuss.88.io/t/ai-frameworks/1739 "2025-04-30T06:01:03Z")
Open Source Frameworks GitHub - neuml/txtai: 💡 All-in-one AI framework for semantic search, LLM orchestration and language model workflows --- ## [Llama](https://discuss.88.io/t/llama/1672)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 1\ **Last updated:** [March 8, 2025, 3:22am UTC](https://discuss.88.io/t/llama/1672 "2025-03-08T03:22:34Z")
Meta Llama Recommended llama models: Llama3.2-vision-11b (6GB) Tool Calling https://www.llama.com/docs/model-cards-and-prompt-formats/llama3\_2/#-llama-3.2-vision-models-(11b/90b)- https://www.llama.com/docs/model-cards-and-prompt-formats/llama3\_1/#-tool-calling-(8b/70b/405b)- --- ## [Openmanus](https://discuss.88.io/t/openmanus/1730)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 1\ **Last updated:** [March 16, 2025, 5:49am UTC](https://discuss.88.io/t/openmanus/1730 "2025-03-16T05:49:44Z")
Multi Agent Note there are some fake "openmanus" forks and sites using the same or similar name - becareful. References https://dev.to/foxgem/openmanus-an-autonomous-agent-platform-8nl https://medium.com/@ai-data-drive/hacking-openmanus-inside-the-world-of-ai-agents-b18fe9aba571 https://github.c… --- ## [Community AI Hardware](https://discuss.88.io/t/community-ai-hardware/1292)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 2\ **Last updated:** [March 5, 2024, 12:55am UTC](https://discuss.88.io/t/community-ai-hardware/1292 "2024-03-05T00:55:14Z")
Introduction State-of-the-art AI accelerators can be out of reach for most people, Partition AI enables expensive hardware to be shared without compromising privacy. Old AI Accelerators (e.g. Google Coral) and Graphics Processing Units (GPUs) from gamers or blockchain miners can be upcycled by the … --- ## [Default Models](https://discuss.88.io/t/default-models/1728)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [March 10, 2025, 7:59am UTC](https://discuss.88.io/t/default-models/1728 "2025-03-10T07:59:55Z")
Same Models Worldwide Partition AI relies on having the SAME set of AI models available on many different Disposable Nodes. 2025 Default Models 2025 default models are small in size for high volume basic usage. Large Language Models deepseek-r1:7b-qwen-distill-q4\_K\_M - 4.7GB llama3.2-vision:11b-i… --- ## [Deep Seek](https://discuss.88.io/t/deep-seek/1719)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 3\ **Last updated:** [March 4, 2025, 8:55am UTC](https://discuss.88.io/t/deep-seek/1719 "2025-03-04T08:55:54Z")
Open Large Language Model As of 2025-03-05, Deepseek R1 is still the ONLY open LLM in the top 10 of most LLM rankings. source: llmarena source: artificialanalysis Distilled Models Many Deepseek R1 models (including distilled models) are now available in quantised format on Ollama. For examp… --- ## [Customising AI](https://discuss.88.io/t/customising-ai/537)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 1\ **Last updated:** [August 18, 2024, 10:28am UTC](https://discuss.88.io/t/customising-ai/537 "2024-08-18T10:28:04Z")
Multiple Solutions The bedrock of Partition AI is for everyone to improve AI models independently - without Cloud Bottleneck. Fine Tuning - expensive Transfer Learning - cheaper Retrieval Augment Generation - cheapest Our focus in on Retrieval Augment Generation (RAG) but other methods are also s… --- ## [Cloud AI](https://discuss.88.io/t/cloud-ai/1524)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [June 16, 2024, 2:18am UTC](https://discuss.88.io/t/cloud-ai/1524 "2024-06-16T02:18:33Z")
Power of AI for Everyone There is Nothing wrong with AI, there is Everything wrong with concentration of AI. Current AI Problems To err is human, to err a thousand times is AI. Deep Learning based Artificial Intelligence requires massive amount of data and compute power, fitting perfectly into … --- ## [Biometrics Authentication](https://discuss.88.io/t/biometrics-authentication/1653)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 1\ **Last updated:** [November 16, 2024, 4:10am UTC](https://discuss.88.io/t/biometrics-authentication/1653 "2024-11-16T04:10:13Z")
Making Biometrics Safe Storing your biometrics on a device (e.g. your phones, laptops etc.) which has continuous software updates, thus guaranteed exposure to supply chain attacks with every update and numerous bugs is extremely dangerous - unlike a password you cannot change them easily if at all -… --- ## [VRAM](https://discuss.88.io/t/vram/1605)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [September 22, 2024, 11:48am UTC](https://discuss.88.io/t/vram/1605 "2024-09-22T11:48:04Z")
VRAM Size Default GPUs with 4GB is above can be use, although having 16GB is recommended. Reference A good indication of VRAM requried for Llama 3.1 (one of the models we support) is available here: --- ## [Speech to Text](https://discuss.88.io/t/speech-to-text/1406)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 9\ **Last updated:** [September 3, 2024, 10:57pm UTC](https://discuss.88.io/t/speech-to-text/1406 "2024-09-03T22:57:28Z")
Speech to Text Speech is a fundamental part of being human. 88.io provides tools to help in the push towards citizens not only owning their data but also the intelligence that comes from their data. A major weakness of many voice recognition system is the sending of your voice to the Cloud for rec… --- ## [AI Interface](https://discuss.88.io/t/ai-interface/1569)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 2\ **Last updated:** [August 10, 2024, 2:51am UTC](https://discuss.88.io/t/ai-interface/1569 "2024-08-10T02:51:10Z")
There are a lot of software in the AI Interface space: Default: GitHub - open-webui/open-webui: User-friendly AI Interface (Supports Ollama, OpenAI API, ...) GitHub - onyx-dot-app/onyx: Open Source AI Platform - AI Chat with advanced features that works with every LLM Others: GitHub - Mintplex… --- ## [Model Formats](https://discuss.88.io/t/model-formats/1580)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [August 24, 2024, 4:20am UTC](https://discuss.88.io/t/model-formats/1580 "2024-08-24T04:20:57Z")
Machine Learning Model Formats --- ## [Agent Commands](https://discuss.88.io/t/agent-commands/1570)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [August 10, 2024, 5:53am UTC](https://discuss.88.io/t/agent-commands/1570 "2024-08-10T05:53:52Z")
Intent GitHub - rapidfuzz/RapidFuzz: Rapid fuzzy string matching in Python using various string metrics --- ## [Huginn](https://discuss.88.io/t/huginn/1566)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [August 10, 2024, 1:50am UTC](https://discuss.88.io/t/huginn/1566 "2024-08-10T01:50:26Z")
Agent Automation The Huggin open source software enables your Entity Agent to handle complex events automatically for you. Tutorial Beginners Huginn: An Open-Source, Self-Hosted IFTTT - DEV Community Advanced Huginn for Newsrooms https://medium.com/@VirtualAdept/huginn-writing-a-simple-agent-… --- ## [Agent Answering Calls](https://discuss.88.io/t/agent-answering-calls/1499)
**Author:** [@admin](https://discuss.88.io/u/admin)\ **Replies:** 0\ **Last updated:** [May 17, 2024, 3:34am UTC](https://discuss.88.io/t/agent-answering-calls/1499 "2024-05-17T03:34:23Z")
Protect Your Phone Number Entity Agents can answer calls for you. Community Phone Number Since the Community Phone Number is shared between many people, it can only answer for calls for you: Direct Call if you dial into your entity agent directly from your verified phone number Forwarded Cal… [Previous page](https://discuss.88.io/c/own-ai/own-interface/desktop-model/313.md) [Next page](https://discuss.88.io/c/own-ai/own-interface/desktop-model/313.md?page=2)