Posted inLocal LLMs
I got the Second DGX spark
Exciting News: Acquiring a Second DGX Spark – What’s Next? In an unexpected turn of events, I was fortunate enough to secure a second NVIDIA DGX Spark at the last…
Posted inLocal LLMs
Deployed Deepseek R1 70B on 8x RTX 3080s: 60 tokens/s for just $6.4K – making AI inference accessible with consumer GPUs
Unlocking Cost-Effective AI Inference with Consumer GPUs: Deploying Deepseek R1 70B on Multiple RTX 3080s In the rapidly evolving field of artificial intelligence, accessibility and cost-efficiency are key to broader…
Posted inLocal LLMs
You can now train your own TTS model 100% locally!
Empower Your Voice Synthesis Projects: Train Custom TTS Models Locally with Unsloth In an exciting development for enthusiasts and professionals in speech synthesis, Unsloth has announced the availability of a…
Posted inLocal LLMs
A warning to newbies – A lesson on network security
A Cautionary Reminder for AI Enthusiasts: The Importance of Robust Network Security As the excitement around deploying large language models (LLMs) locally continues to grow, many enthusiasts are exploring the…
Posted inLocal LLMs
Upgraded to 2x RTX Pro 6000
Transitioning to Dual RTX Pro 6000s: Empowering Local AI Model Deployment As advancements in language models continue at a rapid pace, the ability to efficiently run large AI models locally…
Posted inLocal LLMs
Fixed some of Qwen’s issues, and I got receipts! Published on HF
Advancements in Local Language Model Performance: Introducing Nail and Dagger In the rapidly evolving field of natural language processing, achieving coherent, efficient, and reliable interactions with local models remains a…
Posted inLocal LLMs
Glm-5.1 claims near opus level coding performance: Marketing hype or real? I ran my own tests
Assessing Glm-5.1’s Near-Opus Performance: A Practical Evaluation In the realm of AI-driven audio compression, claims of surpassing or matching the renowned Opus codec often generate skepticism. Recently, I decided to…
Posted inLocal LLMs
I ran Qwen3.8-27B against Opus, Sonnet, GPT and others. Results inside.
In-Depth Evaluation of Latest Open Source and Proprietary Language Models: Qwen3.8-27B vs. Leading Contenders As artificial intelligence continues to evolve rapidly, the release of powerful open-source language models prompts a…
Posted inLocal LLMs
Why does everyone seem to have tons of VRAM ?
Understanding the Growing Trend of High-VRAM Graphics Processing Units in AI Applications In recent discussions across technology forums and social media platforms, a noticeable trend has emerged: the use of…
Posted inLocal LLMs
Qwen3.6-35B-A3B Uncensored Aggressive is out with K_P quants!
Introducing the Qwen 3.6-35B-A3B Uncensored Aggressive Model: Cutting-Edge AI with K_P Quants Support We are excited to announce the release of the latest iteration of the Qwen series: the Qwen…