Artificial Intelligence and Local LLM

PC pour agent IA Hermes local : modèle, contexte et VRAM

PC for local AI agent Hermes: model, context, a...

Run the autonomous agent Hermes from Nous Research locally: persistent memory, self-improvement, over 70 skills, all on your machine without cloud or per-token cost. The guide explains why the 64K...

PC for local AI agent Hermes: model, context, a...

Run the autonomous agent Hermes from Nous Research locally: persistent memory, self-improvement, over 70 skills, all on your machine without cloud or per-token cost. The guide explains why the 64K...

PC for Qwen 3.6: 27B dense or 35B-A3B MoE, whic...

Which PC to use to run Qwen 3.6 locally? The guide first addresses the real question — dense 27B version or MoE 35B-A3B — then details the actual VRAM, pitfalls...

PC for Qwen 3.6: 27B dense or 35B-A3B MoE, whic...

Which PC to use to run Qwen 3.6 locally? The guide first addresses the real question — dense 27B version or MoE 35B-A3B — then details the actual VRAM, pitfalls...

PC for Gemma 4 12B: the ideal workstation

Which PC to run Gemma 4 12B locally? Multimodal, 256K context, Apache 2.0: this model comfortably fits on 16 GB of VRAM. The CoreAI 16 workstation (RTX 5060 Ti 16...

PC for Gemma 4 12B: the ideal workstation

Which PC to run Gemma 4 12B locally? Multimodal, 256K context, Apache 2.0: this model comfortably fits on 16 GB of VRAM. The CoreAI 16 workstation (RTX 5060 Ti 16...

Whisper local 2026: transcribe audio and video ...

Whisper locally: transcribe meetings, interviews, podcasts, and videos with accuracy close to the best services, without any file leaving your machine. Variants (faster-whisper, WhisperX, whisper.cpp), actual hardware requirements, and ready-to-use...

Whisper local 2026: transcribe audio and video ...

Whisper locally: transcribe meetings, interviews, podcasts, and videos with accuracy close to the best services, without any file leaving your machine. Variants (faster-whisper, WhisperX, whisper.cpp), actual hardware requirements, and ready-to-use...

Open WebUI 2026: the ultimate interface to mana...

Open WebUI is the reference interface for running your AI models locally: ChatGPT-style chat, document RAG, multi-user support, compatible with Ollama, vLLM, and LM Studio. Discover its 2026 features, how...

Open WebUI 2026: the ultimate interface to mana...

Open WebUI is the reference interface for running your AI models locally: ChatGPT-style chat, document RAG, multi-user support, compatible with Ollama, vLLM, and LM Studio. Discover its 2026 features, how...

Local AI for Accountants: Balance Sheet Analysi...

Local AI for accountants: analyze balance sheets, trial balances, and financial documents, detect anomalies, and generate your reports without any client data leaving the office. Workstations compliant with professional secrecy...

Local AI for Accountants: Balance Sheet Analysi...

Local AI for accountants: analyze balance sheets, trial balances, and financial documents, detect anomalies, and generate your reports without any client data leaving the office. Workstations compliant with professional secrecy...