August 18, 2026 · 2 min read
The Current State of OpenVINO in llama.cpp
A look at where the OpenVINO backend in llama.cpp stands right now, including recent Qwen3.5 MoE support and my experience trying it.
$ whoami — hadi
Notes & essays, written by hand.
A quiet corner of the internet. No ads on the blog, no autoplay, no noise — just things I'm learning and building, in my own words. Plus a shelf of hands-on posts.
subscribe via RSSLatest from the blog
all blog posts →Posts
all posts → intermediate
Why You Can't Trust LLM Recommendations for Intel AI Hardware
Ask a chatbot about local LLMs on Intel Arc and it names Vulkan, SYCL or a dead IPEX-LLM. It never names OpenVINO, and never names a model from this year.
intermediateHow to Run AI Models on the Intel Arc B580 (12 GB VRAM Guide)
Run local LLMs and vision models on the 12 GB Intel Arc B580 with OpenVINO Model Server: VRAM and KV-cache budget, pre-converted INT4 IR builds, DFlash speculative decoding, and token/s benchmarks.
intermediateBest OpenVINO Models with DFlash Speculative Decoding for Intel Arc and Core Ultra
Pre-converted OpenVINO IR models and matching DFlash speculative-decoding drafts for Intel Arc GPUs and Core Ultra iGPUs, with verified hidden-state locators, stateful KV caches, and measured 2.26x–4.35x speedups.
$ ls content/
All articles
A complete, linkable map of the site: practical guides first, then the hand-written blog. Browse by collection or jump straight to a category.
39 published articles
Guides
open guides page → guide AI October 26, 2026 2 min
Why You Can't Trust LLM Recommendations for Intel AI Hardware
Ask a chatbot about local LLMs on Intel Arc and it names Vulkan, SYCL or a dead IPEX-LLM. It never names OpenVINO, and never names a model from this year.
intel-arcopenvinolocal-llmvram
guide AI October 21, 2026 11 min
How to Run AI Models on the Intel Arc B580 (12 GB VRAM Guide)
Run local LLMs and vision models on the 12 GB Intel Arc B580 with OpenVINO Model Server: VRAM and KV-cache budget, pre-converted INT4 IR builds, DFlash speculative decoding, and token/s benchmarks.
intel-arcarc-b580battlemageopenvino
guide AI October 19, 2026 6 min
Best OpenVINO Models with DFlash Speculative Decoding for Intel Arc and Core Ultra
Pre-converted OpenVINO IR models and matching DFlash speculative-decoding drafts for Intel Arc GPUs and Core Ultra iGPUs, with verified hidden-state locators, stateful KV caches, and measured 2.26x–4.35x speedups.
openvinodflashspeculative-decodingintel-arc
guide Web Development October 18, 2026 3 min
Google AdSense Stuck on Getting Ready? Complete Your Profile First
If AdSense is stuck on “Getting ready,” complete the account setup tasks and check your site connection first. If everything is complete, Google says review can take 2–4 weeks.
google-adsenseadsense-approvalwebsite-monetizationtroubleshooting
guide AI October 18, 2026 8 min
How to Convert an Abliterated (Uncensored) Model to OpenVINO int8 IR
Turn a BF16 abliterated model from Hugging Face into OpenVINO int8 or int4 IR, including a two-stage conversion and thread cap for large MoE models.
openvinomodel-conversionquantizationabliterated
guide AI October 7, 2026 6 min
How to Convert Qwen-Image-2.1 to OpenVINO IR (and Build an Uncensored Version)
Export Qwen-Image-2.1 to OpenVINO IR on Python 3.12: work around the allow_new export crash, quantize the text encoder to INT4 with group_size=-1, and swap in an abliterated encoder for an uncensored build.
openvinomodel-conversionqwen-imagediffusion
guide 3D Printing September 13, 2026 4 min
Elegoo Centauri Carbon 2 Combo Review: Four-Color Printing on a Budget
The cheapest enclosed four-color CoreXY printer you can buy, and the running cost that decides whether it is worth it. Specs, the CANVAS system, and where this machine is the wrong buy.
elegoocentauri-carbon-2centauri-carbon-2-combomulticolor-3d-printing
guide AI September 13, 2026 7 min
How to Run MoE Models on OpenVINO with Disk Streaming
A practical OpenVINO guide to running large Mixture-of-Experts models with GPU memory offloading and disk streaming, including current commands and OVMS deployment examples.
openvinomoedisk-streamingoffload
guide AI September 13, 2026 7 min
What Can You Run on an Intel Core Ultra iGPU with OpenVINO?
A practical RAM-tier guide to running current Qwen models on Intel Core Ultra integrated GPUs with OpenVINO and OVMS, from 16 GB systems through 64 GB configurations.
openvinointel-core-ultraintel-arcigpu
guide AI September 12, 2026 7 min
How OpenVINO MTP Speculative Decoding Works Internally
A technical look at how Optimum Intel exports Qwen3.5 MTP, connects hidden states and shared embeddings, manages KV cache, and integrates the MTP head with OpenVINO speculative decoding.
openvinomtpqwen3.5speculative-decoding
guide AI September 12, 2026 6 min
How to Export Qwen3.5 with an MTP Head to OpenVINO
Export Qwen3.5 MTP models to OpenVINO IR and understand the separate MTP graph, inputs, KV cache, and model-directory layout.
openvinoqwen3.5mtpoptimum-intel
guide Linux September 12, 2026 7 min
How to Troubleshoot Suspend Failures on the Lenovo Yoga 9i Aura with Linux
Troubleshoot Linux laptops that immediately wake from suspend by investigating erroneous wake events from hardware sources such as input devices, the Intel ISH, and other platform devices.
linuxsuspendsleeplenovo-yoga
guide AI September 12, 2026 6 min
How to Use Qwen3.5 MTP Speculative Decoding with OpenVINO
Run Qwen3.5 or Qwen3.5-MoE with OpenVINO MTP speculative decoding, including model export, runtime setup, and the current one-token assistant configuration.
openvinoqwen3.5mtpspeculative-decoding
guide AI August 30, 2026 1 min
How to use DSpark with OpenVINO
DSpark is not currently supported by OpenVINO GenAI, so it cannot be used through the GenAI API.
openvinodsparkspeculative-decodinggenai
guide AI August 24, 2026 16 min
How to Convert and Run DFlash Models with OpenVINO
Export DFlash draft models and their target models to OpenVINO IR, then run speculative decoding with OpenVINO GenAI.
openvinodflashqwen3model-conversion
guide 3D Printing August 24, 2026 5 min
How to Install Creality Helper Script on Creality 3D Printers
Install Creality Helper Script on supported Creality K1 and Ender-3 V3 printers, enable root access, connect over SSH, and install useful Klipper features such as M600 and Moonraker with Fluidd or Mainsail.
crealitycreality-helper-scriptk1ender-3-v3
guide 3D Printing August 24, 2026 6 min
How to Install Moonraker + Fluidd/Mainsail on Creality 3D Printers
Install Moonraker and either Fluidd or Mainsail on a supported Creality printer with Creality Helper Script, verify the services, and safely replace or restore the stock web interface.
crealitycreality-helper-scriptmoonrakerfluidd
guide AI August 22, 2026 3 min
Can You Use OpenVINO on LM Studio?
Explain whether LM Studio can use OpenVINO, what backends LM Studio actually offers, and which OpenVINO, Vulkan, or SYCL route makes sense on Intel Arc.
openvinolm-studiointel-arclinux
guide AI August 19, 2026 6 min
How to Convert Models to OpenVINO IR
A practical guide to converting supported PyTorch, ONNX, TensorFlow, TensorFlow Lite, PaddlePaddle, and JAX/Flax models into OpenVINO Intermediate Representation using the official OpenVINO conversion APIs and CLI.
openvinomodel-conversionmachine-learningonnx
guide Hardware August 18, 2026 4 min
Could Cheap HBM Bring HBM to Consumer GPUs?
If an AI-capex crash caused HBM prices and capacity to collapse, Nvidia could have an economic reason to bring HBM to a GeForce flagship. Here is why an HBM-equipped RTX 6090-class card is plausible, and what would still stand in the way.
hbmnvidiageforcertx
guide AI August 18, 2026 5 min
How to Fix Common Gymnasium Setup Problems
Fix the most common Gymnasium installation and environment errors, including old Gym tutorials, missing extras, rendering dependencies, and Python version issues.
gymnasiumreinforcement-learningpythonopenai-gym
guide AI August 18, 2026 4 min
How to Run llama.cpp on Intel Arc with SYCL
Set up llama.cpp's SYCL backend for Intel Arc and understand the Intel oneAPI pieces behind it.
intel-arcsyclllama-cpponeapi
guide AI August 18, 2026 3 min
How to Run Local LLMs on Intel Arc with Vulkan
Use Vulkan-based local LLM applications on Intel Arc, including llama.cpp, LM Studio, and Ollama.
intel-arcvulkanllama-cppollama
guide AI August 18, 2026 4 min
How to Run Local LLMs on Intel Arc
A practical guide to running local LLMs on Intel Arc: which card you need, how much VRAM each model class requires, and the SYCL, Vulkan, and OpenVINO routes compared.
intel-arclocal-llmsyclvulkan
guide AI August 18, 2026 4 min
How to Run Local LLMs with OpenVINO on Intel Arc
Use Intel OpenVINO for local LLM inference on Arc GPUs and understand where OpenVINO, OVMS, and related runtimes fit.
intel-arcopenvinoovmslocal-llm
guide AI August 18, 2026 4 min
How to Set Up OpenAI Gymnasium
Install Gymnasium in an isolated Python environment, run a verified CartPole example, understand the reset and step API, and add optional environment families safely.
gymnasiumreinforcement-learningpythonopenai-gym
guide Ebooks August 18, 2026 5 min
How to Use OPDS with KOReader
Set up an OPDS catalog in KOReader to browse and download ebooks directly from your library.
koreaderopdsebooksereader
guide AI August 17, 2026 3 min
How to Build and Secure an MCP Server for AI Agents
Build and secure an MCP server so AI agents can use your tools: HTTP transport, authentication, and rate limiting, step by step.
mcpai-agentsserversecurity
guide Security August 17, 2026 2 min
How to Set Up Cloudflare WAF Rules and Rate Limiting
Harden your Cloudflare site with WAF custom rules and rate limiting. A practical guide to blocking bots and abusive traffic.
cloudflaresecuritywafrate-limiting
guide Git August 17, 2026 3 min
How to Set Up Git and GitHub from the Command Line
Set up Git and GitHub from the command line: SSH keys, your first commit, branches, and pull requests. Everything you need to start version-controlling projects.
gitgithubsshversion-control
guide DevOps August 17, 2026 3 min
How to Set Up GitHub Actions for CI/CD
Set up GitHub Actions for continuous integration and deployment. Automate tests and deploys on every push with a reusable workflow.
github-actionsci-cddevopsdeployment
guide Development Environment August 17, 2026 5 min
How to Set Up a Modern JavaScript Development Environment
Set up Node.js, npm, Git, and VS Code for a reproducible JavaScript workflow, then verify the environment with a small project.
nodegitvscodesetup
guide Databases August 17, 2026 2 min
How to Set Up a Serverless Postgres Database with Neon and Drizzle
Set up a serverless Postgres database with Neon and Drizzle ORM: schema, migrations, and queries without managing servers.
postgresneondrizzledatabase
guide AI August 17, 2026 3 min
How to Set Up OpenRouter as Your AI Provider
Set up OpenRouter as your AI provider: API keys, the OpenAI-compatible endpoint, and model selection for your apps and agents.
aiopenrouterllmapi
guide TypeScript August 17, 2026 3 min
How to Set Up a TypeScript Project from Scratch
Create a TypeScript project from scratch: tsconfig.json, strict mode, and build scripts. A hands-on setup guide for Node.js and TypeScript.
typescriptnodesetup
guide Tooling August 17, 2026 5 min
How to Set Up VS Code for Web Development
Configure VS Code for web development with focused extensions, workspace settings, formatting, linting, debugging, and an integrated terminal.
vscodeeditorproductivitytooling
guide Cloudflare August 17, 2026 6 min
How to Set Up Wrangler for Cloudflare Workers Development
Install and configure Wrangler for local Cloudflare Workers and Pages development, including environment variables, KV bindings, secrets, environments, and deployment.
cloudflareworkerswranglercli
guide Web August 13, 2026 3 min
How to Deploy an Astro Content Site on Cloudflare Pages
A hands-on walkthrough of building a Git-backed content site with Astro and shipping it to Cloudflare Pages with zero database.
astrocloudflarestatic-sitedeployment
Blog
open blog page →Hand-written notes and essays, kept separate from the how-to guides.