#gptoss — Public Fediverse posts

Развиваем ИИ-платформу в 1С

Статья о том, как мы пришли к ИИ для 1С и что из этого вышло. Материал получился про попытку собрать полноценную ИИ-платформу для работы с учетными данными. Расскажу, зачем нам понадобился MCP, как мы связали его с 1С:Шина, почему отдельно уперлись в права доступа и как в итоге устроили агента внутри 1С. Также покажу, где видим место для skills, RAG и OCR, и что пока не стали отдавать модели на самостоятельное выполнение.

https://habr.com/ru/companies/cinimex/articles/1046197/

#1с #иипомощник #mcpserver #function_calling #агент #rag #ocr #права_доступа #локальные_модели #gptoss

Миф о «равных весах»: что на самом деле скрывается внутри малых моделей

Последние годы развитие LLM шло по пути экстенсивного масштабирования: считалось, что чем больше весов и данных, тем умнее модель. В индустрии даже сложилась жесткая классификация по количеству параметров: 7B, 8B, 32B. Она же создает иллюзию, что модели одной весовой категории обладают сопоставимыми аналитическими, генеративными и логическими характеристиками, что в корне противоречит современным эмпирическим наблюдениям. Но действительно ли «вес» модели все еще определяет ее качество в 2026 году? Или компактная архитектура способна конкурировать с гигантами, требующими H100 и сотни гигабайт VRAM? В этой статье мы не будем рассуждать об этом абстрактно: возьмем реальные модели из каталога FMC и посмотрим на практике, как размер влияет на качество reasoning, генерации и прикладную эффективность — и влияет ли вообще.

https://habr.com/ru/companies/selectel/articles/1043278/

#mlops #selectel #llmмодели #qwen #phi4 #mistral #gptoss #deepseek #ai #aiагенты

Neste vídeo, eu testei diferentes modelos de inteligência artificial rodando localmente no Linux Mint utilizando o LM Studio.
O objetivo foi verificar se essas IAs conseguem responder corretamente perguntas simples — desde fatos pouco conhecidos, como o primeiro vocalista do Iron Maiden, até informações mais populares, como quem criou o kernel Linux.

Link: https://youtu.be/F8A2Yx4an_M

#inteligenciaartificial #lmstudio #ialocal #ibmgranite #gptoss #googlegemma #qwen #rx550 #linux

Neste vídeo, eu testei diferentes modelos de inteligência artificial rodando localmente no Linux Mint utilizando o LM Studio.
O objetivo foi verificar se essas IAs conseguem responder corretamente perguntas simples — desde fatos pouco conhecidos, como o primeiro vocalista do Iron Maiden, até informações mais populares, como quem criou o kernel Linux.

Link: https://youtu.be/F8A2Yx4an_M

#inteligenciaartificial #lmstudio #ialocal #ibmgranite #gptoss #googlegemma #qwen #rx550 #linux

New week, more slides: Run LLMs Locally

Now with LFM 2 and new slides for using Transformers.js with WebGPU for Privacy Filter, Function Calling and Embeddings, running completely in your browser.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #gemma4 #nemotron #webgpu

New week, more slides: Run LLMs Locally

Now with LFM 2 and new slides for using Transformers.js with WebGPU for Privacy Filter, Function Calling and Embeddings, running completely in your browser.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #gemma4 #nemotron #webgpu

TUTORIAL - Passo a passo: IA local no Linux com LM Studio

Neste vídeo, você vai aprender como rodar inteligência artificial localmente no seu Linux usando o LM Studio.

Se você quer mais controle, mais privacidade e rodar IA direto no seu computador, esse guia é pra você.

Link: https://youtu.be/M7jR2BIuGyQ

#debian #debian13 #lmstudio #ialocal #ibmgranite #gptoss #googlegemma #qwen #rx550 #linux

TUTORIAL - Passo a passo: IA local no Linux com LM Studio

Neste vídeo, você vai aprender como rodar inteligência artificial localmente no seu Linux usando o LM Studio.

Se você quer mais controle, mais privacidade e rodar IA direto no seu computador, esse guia é pra você.

Link: https://youtu.be/M7jR2BIuGyQ

#debian #debian13 #lmstudio #ialocal #ibmgranite #gptoss #googlegemma #qwen #rx550 #linux

New week, new slides: Run LLMs Locally

Now including Nemotron 3 Nano Omni from Nvidia, Llama.cpp built-in tools and new slides about using Transformers.js with WebGPU for Image Recognition and OCR.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #gemma4 #nemotron #webgpu

New week, new slides: Run LLMs Locally

Now including Nemotron 3 Nano Omni from Nvidia, Llama.cpp built-in tools and new slides about using Transformers.js with WebGPU for Image Recognition and OCR.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #gemma4 #nemotron #webgpu

🔧 Fine-tunable on domain-specific data — adapts to medical, legal or enterprise environments where generic rules fail. Based on the open #gptoss model family. Available on #HuggingFace under Apache 2.0

🚨 Caveat: #PrivacyFilter is a redaction & data minimization aid — NOT a compliance guarantee. It should be one layer in a holistic #privacybydesign approach. Always combine with human review for high-stakes use cases
https://openai.com/index/introducing-openai-privacy-filter/

🔧 Fine-tunable on domain-specific data — adapts to medical, legal or enterprise environments where generic rules fail. Based on the open #gptoss model family. Available on #HuggingFace under Apache 2.0

🚨 Caveat: #PrivacyFilter is a redaction & data minimization aid — NOT a compliance guarantee. It should be one layer in a holistic #privacybydesign approach. Always combine with human review for high-stakes use cases
https://openai.com/index/introducing-openai-privacy-filter/

New week, new update for the slides of my talk "Run LLMs Locally":

Now including Gemma4 and Qwen3-Omni with Vision and Audio support and new slides describing Llama.cpp server parameters.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #gemma4

New week, new update for the slides of my talk "Run LLMs Locally":

Now including Gemma4 and Qwen3-Omni with Vision and Audio support and new slides describing Llama.cpp server parameters.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #gemma4

New update for the slides of my talk "Run LLMs Locally": Bonsai-8B

The latest version of Llama.cpp now supports Vulkan with 1-bit quantized models like Bonsai: 8B model having 1.1 GB in size, 2.5 GB in RAM.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai

New update for the slides of my talk "Run LLMs Locally": Bonsai-8B

The latest version of Llama.cpp now supports Vulkan with 1-bit quantized models like Bonsai: 8B model having 1.1 GB in size, 2.5 GB in RAM.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai

New update for the slides of my talk "Run LLMs Locally": WebGPU

Now models can run completely inside the browser using Transformers.js, Vulkan and WebGPU (slower than llama.cpp, but already usable).

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #webgpu

don't expect llm generated code to be correct ↓

New update for the slides of my talk "Run LLMs Locally": WebGPU

Now models can run completely inside the browser using Transformers.js, Vulkan and WebGPU (slower than llama.cpp, but already usable).

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai #webgpu

don't expect llm generated code to be correct ↓

New update for the slides of my talk "Run LLMs Locally":

Now including music generation with ACE-Step and OCR using LightOnOCR.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai

New update for the slides of my talk "Run LLMs Locally":

Now including music generation with ACE-Step and OCR using LightOnOCR.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#ai #llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #localai

Облачные модели Ollama в задачах code review — честное сравнение на примерах

AI всё чаще используется в разработке: генерация кода, автодополнение, агентные IDE. Но возникает логичный вопрос - можно ли доверить LLM полноценный code review? В этой статье я решил проверить это на практике. Я сравнил несколько моделей, доступных через Ollama Cloud - Qwen 3.5, GPT-OSS и DeepSeek v3.1 - и дал им проанализировать реальные Pull Request из легаси-проекта на Python. Спойлер: некоторые модели показали неожиданно хороший результат.

https://habr.com/ru/articles/1010048/

#code_review #ollama #llm #ai_code_review #pull_request #github #open_source #deepseek #qwen #gptoss

New update for the slides of my talk "Run LLMs Locally":

Now including Reranking, Qwen 3.5 (slower than Qwen 3, but includes Vision) and loading models with Direct I/O.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #localai #mcp

New update for the slides of my talk "Run LLMs Locally":

Now including Reranking, Qwen 3.5 (slower than Qwen 3, but includes Vision) and loading models with Direct I/O.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2025_ThomasBley.pdf

#llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #localai #mcp

One more update for the slides of my talk "Run LLMs Locally":

Now including text to speech with Qwen3-TTS and Model Context Protocol.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #localai #mcp

One more update for the slides of my talk "Run LLMs Locally":

Now including text to speech with Qwen3-TTS and Model Context Protocol.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2025_ThomasBley.pdf

#llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #localai #mcp

I updated the slides for my talk "Run LLMs Locally":

Now including image generation with Qwen3 and content classification from the Qwen3Guard Technical Report paper.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #localai

I updated the slides for my talk "Run LLMs Locally":

Now including image generation with Qwen3 and content classification from the Qwen3Guard Technical Report paper.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2025_ThomasBley.pdf

#llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #localai

Tell ya what, #Mailroute + #Sortana / #gptoss has made my #email manageable for the first time in maybe 2 decades. Truly amazing.

Tell ya what, #Mailroute + #Sortana / #gptoss has made my #email manageable for the first time in maybe 2 decades. Truly amazing.

New talk coming tomorrow: Run LLMs locally

I will present it @phpugmrn in Mannheim.

#llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #ocr #localai #security

New talk coming tomorrow: Run LLMs locally

I will present it @phpugmrn in Mannheim.

#llm #llamacpp #stablediffusion #gptoss #qwen3 #glm #ocr #localai #security

DES-Projekt Hochschulschriften: Unterstützung aus Frankreich

https://www.compgen.de/2026/03/des-projekt-hochschulschriften-unterstuetzung-aus-frankreich/

I updated the slides for my talk "Run LLMs Locally":

Now including remote code execution with Skills, ascii smuggling and extended embeddings slide.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #localai #security

I updated the slides for my talk "Run LLMs Locally":

Now including remote code execution with Skills, ascii smuggling and extended embeddings slide.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2025_ThomasBley.pdf

#llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #localai #security

I updated the slides for my talk "Run LLMs Locally":

Now including OCR, Qwen3-Coder, GLM-Flash and more links on the resources slide.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #php #digitalsovereignty #localai

I updated the slides for my talk "Run LLMs Locally":

Now including OCR, Qwen3-Coder, GLM-Flash and more links on the resources slide.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#llm #llamacpp #ollama #stablediffusion #gptoss #qwen3 #glm #opencode #php #digitalsovereignty #localai

I updated the slides for my talk "Run LLMs Locally":

Now including requirements, costs, setup, llama.cpp, stable-diffusion.cpp, embeddings, function calling, opencode, image recognition, speech recognition, image generation, prompt injection and popular models like GPT-OSS, Qwen3, Qwen3-vl, Z-Image and Whisper.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#llm #llamacpp #stablediffusion #gptoss #qwen3 #opencode #php #digitalsovereignty #localai

I updated the slides for my talk "Run LLMs Locally":

Now including requirements, costs, setup, llama.cpp, stable-diffusion.cpp, embeddings, function calling, opencode, image recognition, speech recognition, image generation, prompt injection and popular models like GPT-OSS, Qwen3, Qwen3-vl, Z-Image and Whisper.

https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#llm #llamacpp #stablediffusion #gptoss #qwen3 #opencode #php #digitalsovereignty #localai

Doing some sprucing up on my #AI #LLM powered #email filtering/tagging #Thunderbird add-on #Sortana. I had got it working with #Qwen, but realized it really didn't work for other model chat formats.

Trying it now with #gptoss (4bit quant) and in testing it is pretty fast. Pleased so far.

EdgeRunner AI just launched an offline assistant built on the open-source gpt-oss model, marking the first time open-weight LLMs are deployed with the US Army and Air Force. This could reshape how the military uses AI without internet reliance. Read more to see the implications for open-source AI and defense. #EdgeRunnerAI #gptOSS #OpenWeightModels #USMilitary

🔗 https://aidailypost.com/news/edgerunner-ai-runs-assistant-gpt-oss-open-weight-models-join-us

I've written a new talk :)

Run LLMs _locally_ with integrated AMD GPUs and unified memory:
https://codeberg.org/thbley/talks/raw/branch/main/Run_LLMs_Locally_2026_ThomasBley.pdf

#llm #llamacpp #gptoss #qwen3 #curl #php

OpenAI will ChatGPT zum zukünftigen Betriebssystem machen
OpenAI will ChatGPT auf eine neue Stufe heben und zeigt, wie Apps künftig direkt in die Chat-Oberfläche eingebettet werden. Auf der Entwicklerkonferenz in San Franc
https://www.apfeltalk.de/magazin/news/openai-will-chatgpt-zum-zukuenftigen-betriebssystem-machen/
#KI #News #Apps #Betriebssystem #Canva #chatGPT #Codex #Entwickler #Entwicklerkonferenz #GPT5 #GPTOSS #KIAgenten #Monetarisierung #OpenAI #SamAltman #SDK #Spotify #Zillow