#VRAM usage
345 related articles
·3 min
Unsloth Major Update: GLM-5.2 Support, 3x Longer Context, and a New Model Hub
Unsloth v0.1.471-beta adds full GLM-5.2 support, 3x longer context (up to 200K tokens on a single GPU), a new Model Hub, and Chat Canvas — a major leap for local LLM fine-tuning.
Read more →
·3 min
Unsloth Major Update: DiffusionGemma & Gemma 4 MTP Support, 2x Inference Speed Boost
Unsloth v0.1.464-beta adds DiffusionGemma, Gemma 4 MTP, and MiniMax-M3 support, delivering ~2x inference speed boost, new Hub, RAG Q&A, tensor parallelism, and full CUDA/ROCm/Windows coverage.
Read more →
·1 min
Unsloth v0.1.47-beta Released: 2x Faster LLM Fine-Tuning with 70% Less VRAM
Unsloth v0.1.47-beta is out. This 67.9k-star open-source framework fine-tunes Llama, Mistral, and Qwen 2x faster with 70% less VRAM on consumer GPUs.
Read more →
·3 min
AMD Ryzen AI Halo Local AI Dev Kit Deep Dive: Is $4,000 Worth It?
AMD Ryzen AI Halo dev kit at $4,000 features 128GB unified memory and XDNA 2 NPU for local LLM inference. Deep dive into architecture, performance trade-offs, vs. Mac Studio, and software ecosystem challenges.
Read more →
·3 min
AI Agent Fully Automates TV Subtitle Generation: From Audio Extraction to Final Output in One Go
How does AI Agent automate TV subtitle workflows end-to-end? This demo covers audio extraction, ASR, timestamp sync, and line optimization — GLM5 processes a 26-min video in just 10 minutes.
Read more →
·6 min
Codex Configuration in Practice: A Complete Guide to Accessing GPT-5.5 at Low Cost from China
A detailed guide for Chinese developers on configuring the Codex CLI AI coding tool with GPT-5.5 via API proxies, covering setup steps, efficiency gains, and security risks.
Read more →
·5 min
Natively Porting Command & Conquer: Generals to macOS and iOS with the Fable Framework
Using the Fable porting framework, Command & Conquer: Generals has been natively ported to macOS, iPhone, and iPad. Explores DirectX-to-Metal challenges, touch adaptation, and game preservation.
Read more →
·4 min
Frontend to Full-Stack AI: A Complete NestJS + LangChain Roadmap
Pure frontend roles are shrinking fast. Learn how mastering NestJS and LangChain AI agent development can unlock a 20–30% salary boost on your full-stack AI transition path.
Read more →
·6 min
A 284B Model Running on a MacBook: The Real Breakthrough and Barriers of Local DeepSeek Inference
Redis creator runs 284B-parameter DeepSeek model on a MacBook Pro at 26 tokens/sec using a pure C engine, asymmetric quantization, and MoE architecture.
Read more →
·3 min
GLM-4 Open Source Strikes Back: The AI War Expands to Memory and Space Computing
Zhipu AI's GLM open-source model approaches top closed-source models at 15% of GPT-5.5's cost. HBM shortages fuel AI inflation, and space data centers emerge as a serious compute play.
Read more →
·3 min
Running Local LLMs on AMD GPUs: Ditching Ollama for LM Studio Delivers 7x Speed Boost
AMD GPU black screens running local LLMs? This post-mortem covers Ollama's 3 fatal flaws and how switching to LM Studio boosted token speed from 5 to 36, with ROCm setup, Speculative Decoding, and GFX version tips.
Read more →
·2 min
Ollama: The 175K-Star Tool for Running Local LLMs with One Command
Ollama is an open-source local LLM runner with 175K+ GitHub Stars. Built in Go, it supports Llama, Mistral, Qwen and more — deploy in 3 steps, no setup headaches.
Read more →
·6 min
Dify Self-Hosted Deployment in Practice: Building an Enterprise-Grade AI Application Platform from Scratch
A complete guide to self-hosting Dify, the open-source AI platform: environment setup, Docker Compose deployment, LLM integration, and app building. Runs on just 2 cores and 4GB RAM.
Read more →
·4 min
The Complete Guide to Running GLM-5.2 Locally with 4 RTX 3090s for $4,000
How to build a local AI inference server with 4 used RTX 3090 SXM4 GPUs to run GLM-5.2 via Llama.cpp and Unsloth IQ quantization, with real benchmarks on speed and quality.
Read more →
·3 min
Deploy a Free AI Agent Locally: Build an All-in-One Assistant with Qwen 3.5 + Hormis
Learn how to deploy a free AI agent locally using Ollama + Qwen 3.5-9B + Hormis framework, enabling web scraping, desktop control, and file management on consumer hardware.
Read more →
·3 min
Ideogram 4 Fully Automated Workflow: Run Locally with Just 8GB VRAM, No Complex Prompts Needed
Ideogram 4 automated ComfyUI workflow using Qwen2.5 VL-8B: run locally with 8GB VRAM, auto-generate structured JSON prompts from simple descriptions, with image reverse-engineering support.
Read more →
·3 min
In-Depth Review of Free AI Aggregator Sites: Is It Legit to Freeload GPT-5.5 and Grok 4.2?
In-depth analysis of free AI aggregator sites popular on Bilibili, exposing reverse proxy and shared account pool mechanics, data privacy risks, and safer alternatives for multi-model AI usage.
Read more →
·2 min
Are AI Aggregation Platforms Reliable? The Truth and Risks Behind One-Stop Access to Multiple LLMs
In-depth analysis of AI aggregation platforms: the truth behind free access to GPT, Gemini, Claude and other LLMs, hidden costs, privacy risks, and safer alternatives.
Read more →
·3 min
The Ultimate Ollama Guide: A Complete Walkthrough for Running AI Models Locally
Complete Ollama guide: install and run open-source LLMs like DeepSeek, Llama, and Qwen locally on Windows/Mac/Linux. Free, private, and beginner-friendly.
Read more →
·2 min
XiaoWu Voice Input Method: Powered by Local LLMs for Accurate Offline Speech Recognition
XiaoWu is a fully local AI voice input method powered by on-device LLMs for accurate offline speech recognition, smart punctuation, and minimalist interaction — no internet required.
Read more →